Search Program

Tetsuaki Baba

‘Battlefield 6’: How We Brought The Franchise Vision To Life With Our Destruction System Debut

Games Summit

11:30am - 12:00pm PDT Sunday, 19 July 2026 411 Theatre

Arts & Design

Gaming & Interactive

Art

Games

Performance

Real-Time

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionBattlefield 6 redefines destruction as a tactical ecosystem rather than visual spectacle. Through ten interrelated destruction elements, systemic and pre-simulated workflows, consistent material damage classes, and shared pipelines, destruction reshapes gameplay spaces, enhances player agency, and delivers immersive, readable, and scalable battlefield experiences that fulfills franchise vision.

People

Educator's Forum

“Live from LA!”: Facilitating Personal and Political Storytelling through Immersive Youth Theater

2:00pm - 2:20pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Capture/Scanning

Education

Ethics and Society

Generative AI

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

Description“Live from LA!” is an immersive youth-theater production blending dance, poetry, and projection-mapping. We discuss how we scaffolded this production across disciplines, locations, and age groups to support youth political storytelling through personal narratives. We highlight how p5.js tools supported youth authorship while navigating practical constraints and safety.

People

Ana Cardenas Gasca

Payton Croskey

Xin Xin

Jennifer Jacobs

1. AI Score Hallucination in Vision-Language Models: Measuring Self-Assessment Calibration for Iterative 3D Scene Positioning

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionStoryboardTo3D uses vision-language models to iteratively position 3D objects from hand-drawn storyboards in Unreal Engine 5.6. Across three VLMs and 36 scenarios, I characterized AI Score Hallucination: a 37.2 percentage point gap between models' self-reported scores and expert-validated success, with implications for VLM-as-judge stopping criteria in creative pipelines.

People

Tyler Varacchi

Drexel University

Poster

10. Motion-Faithful Denoising for Dynamic Facial Scan Sequences

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionHigh-fidelity dynamic facial scans are essential to modern film VFX, but they suffer from tracking jitter — a subtle frame-to-frame shaking that appears when each frame is captured and registered independently. Standard denoisers can't fix it: they either ignore time or blur away the very expressions that make a performance believable. We introduce a motion-adaptive bilateral temporal filter that smooths along the time axis while letting local motion preserve fast expressions. It removes jitter, cutting temporal error by up to 76% over uniform filters, and drops straight into existing production pipelines.

People

Poster

11. Natural-Language to Geometry Diagrams: A Constraint-Based Pipeline for Precise Visual Reasoning

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present GenGX, a pipeline converting natural language geometry descriptions into diagrams, using an LLM to convert the input into a structured intermediate representation, which a symbolic constraint solver (CoreGX) then realizes deterministically.

People

Poster

12. Single-Stroke Inflatable Tubes Deforming into Freeform Planar Curves

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose a computational design and roll-to-roll fabrication method for single-stroke inflatable tubes that deform into freeform planar curves, enabling easy and fast fabrication in a compact workspace.

People

13. Tex-Shadow: Synthesizing Textured 3D Shadow Art via 3D-Aware Diffusion Prior

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionTex-Shadow introduces a novel optimization pipeline leveraging 3D-aware diffusion priors and differentiable rendering to automate the creation of textured 3D shadow art from semantic-free image inputs. By synthesizing complex 3D geometries and UV textures, our method produces high-quality results supporting diverse downstream applications — including physical fabrication, interactive game assets, and immersive virtual art exhibitions with minimal manual effort.

People

Poster

15. Where to Learn Matters: Feature-Aware Sampling for Neural SDF Reconstruction

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a simple, plug-and-play two-stage adaptive sampling strategy for neural signed-distance-field reconstruction that reallocates training toward geometrically informative regions, improving frame fidelity, sharp-feature recovery, and overall reconstruction quality on the ABC benchmark without changing the underlying network architecture or reconstruction loss.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Haotian Yin

New Jersey Institute of Technology

Jiaxing Zhang

Zhiqiang Lao

Yu Guo

Yuanpeng Liu

Stony Brook University

Jiali Cui

Heather Yu

Przemyslaw Musialski

16. A DEM-Integrated Stream-Function Solver for Simulating Sand Motion in Liquid–Bubble Flows

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a DEM-integrated stream-function solver for simulating sand motion in liquid-bubble flows. By coupling a stream-function fluid solver with DEM, our method models liquid forces and collisions with moving bubble interfaces, producing plausible underwater sand transport and interface-following sand motion.

People

17. Appearance-Invariant Detection of Suggestive Motion via Laban Movement Descriptors

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a privacy-preserving moderation pipeline that flags suggestive motion in online virtual environments from body movement alone -- no pixels, clothing, or body shape -- by classifying interpretable Laban Movement Analysis descriptors computed from 3D skeletons, matching a fine-tuned deep video model on the same appearance-free motion while computationally confirming choreographic theory's prediction that suggestiveness is carried by indirect use of space.

People

Computer Animation Festival

18 Months

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

Description“18 Months” is a true story about the unexpected paths to becoming a family. When Danny and Pete find a newborn in a subway station, their journey to adopt him is retold to mirror the stages of pregnancy—challenging traditional definitions and proving it doesn't always take a man, a woman, and 9 months to build a family.

People

Director

Director

Poster

18. BlendAnything: A Blender Plugin for Cross-Topology Motion Blending

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionBlendAnything is a Blender plugin that enables cross-topology motion blending through a skeleton-agnostic diffusion autoencoding backend to interpolate between heterogeneous character structures. The system empowers animators to seamlessly transition motions across diverse skeletons, such as crabs and coyotes, directly within the NLA Editor.

People

Poster

19. Deploying Speech-Driven 3D Facial Animation in Unreal Engine for Production-Ready Digital Humans

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionSpeech-driven facial animation has advanced rapidly, yet most methods remain incompatible with production pipelines. We bridge this gap by enabling speech-driven animation in Unreal Engine using ARKit. We build a dataset, retrain state-of-the-art models, and develop a modular plugin for controllable, production-ready animation.

People

Poster

2. Aurora: Real-Time Co-Sculpting of Mesh-Based Multi-Agent Geometry for Fabrication-Aware Design

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionAurora is a real-time co-sculpting system for fabrication-aware architectural mesh design. It enables designers to paint behavioural activity, sculpt dense multi-agent geometry, and read curvature and draft-angle analysis overlays within one live viewport. By keeping gesture, simulation, and fabrication feedback active in the same modelling session, Aurora allows emergent ornamental geometry to be redirected, repaired, and fabrication-tuned during form finding. The system is demonstrated through built polymer and sandstone fabrication projects.

People

Marc Gibson

RMIT University

Poster

20. Fast Modal Dynamics for Hairy and Scaly Surfaces on the GPU

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a reduced order method for finite element simulation of almost a million short furs, spikes or scales attached to a deforming mesh, in real time (28FPS).

People

Yixin Lok

David I.W. Levin

21. From State Reconstruction to State Interpretation: S2VMO, an Agentic Voxel-Based Digital Twin for Space Habitat Structural Monitoring

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionMonitoring the structural state of space habitats is difficult where sensing is sparse and conditions are too complex for routine inspection, demanding an active, context-aware expert in the loop. S2VMO is a pilot framework that introduces an agentic voxel-based digital twin, which combines finite element modeling, neural field reconstruction, and a GraphRAG multi-agent system to achieve real-time, explainable structural health monitoring and continuous physical state understanding for space habitats using sparse sensor data.

People

Poster

22. Geometry-Aware Table Tennis Racket Pose Estimation via Multi-View Consistency and Racket Priors

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a geometry-driven framework for estimating table tennis racket pose under occlusion. By enforcing cross-view consistency, our method achieves accurate and stable pose estimation. An interactive editing tool is further introduced to generate high-quality ground truth, improving physical plausibility and temporal consistency.

People

Szu-Han Wu

Pei-Hsin Huang

Pu Ching

Hung-Kuo Chu

Min-Chun Hu

23. Learning Surfing-like Balance without Water Simulation

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a method for learning surfing-like balance control without water simulation, enabling a humanoid to maintain stable balance on a moving board under wave conditions despite being trained entirely in non-fluid environments.

People

Poster

24. Multi Layered RBD Simulation

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionI present a multi-layered RBD workflow that enables destruction simulations to be refined through additional simulation layers while preserving approved motion. Fracture detail and art-direction changes can be incorporated incrementally without rebuilding the original simulation.

People

JAE JUN YI

25. OmniBody: Discretized Local Constraints for Real-Time Destructible and Flexible Soft Bodies Simulation

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionOmniBody introduces a scalable GPU framework for real-time soft-body simulation that enables global deformation and emergent anisotropic fracture through local interactions of oriented ellipsoidal particles, eliminating the need for global solvers or complex re-meshing while ensuring high-fidelity, parallelizable performance.

People

Jewoo Shin

Korea Advanced Institute of Science and Technology (KAIST)

Jinah Park

Korea Advanced Institute of Science and Technology (KAIST)

Poster

26. PressureBlush: Real-Time Blanching and Hyperemia Shading from Neural Deformation Signals

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionPressureBlush presents a real-time deformation-to-appearance framework that maps self-contact neural deformation signals to shader-computed blanching and hyperemia, producing physiologically motivated skin-color responses without additional runtime simulation, precomputed textures, or artist-authored masks.

People

Woonjung Kim

Nexon Games

Haemin Kim

27. SeatSwap: Learning-Assisted Differentiable Kinematics for Human-Object Interaction Adaptation in Production-Scale Character Animation

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionSeatSwap solves motion capture data scarcity through a learning-assisted, differentiable biomechanical optimization framework that automatically adapts human animations to arbitrary 3D furniture geometries, unlocking limitless synthetic data generation at production scale.

People

Priyamvad Ravindra Deshmukh

Poster

28. Agriculture Punk: Hello World from Breadboard Farming

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionAgriculture Punk is proposed as a movement toward the computerization of farmland, grounded in an operational isomorphism in which fields have long engaged invisible forces—such as the paddy deity housed in a scarecrow—through the insertion and removal of objects, just as breadboards route electricity through the plugging and unplugging of components; building on this analogy, the work presents Breadboard Farming as its first artistic practice, redesigning field implements such as scarecrows into electronic component-themed tools modeled on LEDs, capacitors, and jumper wires, deploying them across a rice field, a cabbage field, and a harvest festival to redescribe agricultural observation, situated judgment, local belief, and ritual through the vocabulary of electronics prototyping, and implementing a UWB/BLE system that estimates tool positions to form a virtual breadboard layer, thereby realizing breadboard-style connections across physical farmland and opening a technically grounded media-art practice between agriculture, ritual, and computation.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Yuki Horiuchi

Karen Furuta

Jingjing Li

Yoichi Ochiai

29. Cross-Species Empathy Through Multisensory Interaction

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionEmpathic Growth 2.0 is an interactive biodigital installation that explores plant sensing from a more-than-human perspective. Using affective computing and autonomous agents, it translates human and plant biosignals into hybrid digital entities, sound, and responsive light, inviting reflection on sensing, translation, and nonhuman presence.

People

Jia-Qi Shi

Hong Kong University of Science and Technology, Guangzhou

Hankun Yu

Goldsmiths, University of London

Zhecheng Zhang

China Academy of Art, Hangzhou

Meng Yang

Monash University

Ziwei Wu

Hong Kong University of Science and Technology, Guangzhou

Kang Zhang

Technical Paper

2D Gaussian Splatting for Bézier Spline Line Art Vectorization

10:55am - 11:05am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a state-of-the-art vectorization method using depth and semantic features to extract strokes. By modeling Bézier curves via differentiable 2D Gaussian splatting, we efficiently optimize geometry and texture. The framework extends to video for temporal consistency, offering high-quality, user-adjustable results for image and animation reconstruction.

People

Tianhao Chen

ETH Zurich

Clara Fernandez

Marteinn Oskarsson

Chuck Tappan

Abdelaziz Djelouah

3. Cage-based Texture Transfer with Geometric Filtering

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionTraditional texture transfer methods are time consuming and introduce artifacts. We present a cage-based geometric filtering method that uses identification of Non Cosmetic Zones. By leveraging spatial relationships between target and cage meshes through geometry intersections and mesh segmentations, our generalizable approach achieves high-fidelity with low latency on mobile hardware.

People

Rose Mei Zhou

Roblox

Lynnette Hui Xian Ng

30. (Geo) Musical Configurations: A Parametric Framework for Translating Musical Data into Planar Geometric Compositions

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

Description(Geo) Musical Configurations is a rule-based parametric system that translates musical data, including rhythm, pitch, amplitude, and various psychoacoustic descriptors, into planar geometric compositions. Musical data is retrieved through the Spotify Web API, parsed into predefined parameter sets, and mapped to geometric attributes within the visual programming environment of Grasshopper.

This work participates in an ongoing disciplinary shift within the creative fields, where authorship is increasingly displaced from the direct production of form toward the design of systems that generate form. In this context, the role of the designer is no longer to manually compose outcomes, but to construct rule-based frameworks capable of producing a range of possible results. This redefinition of authorship is central to contemporary digital practices across the AEC industry and related creative disciplines.

People

Samantha Shanne

Sarah Hammond

31. Growing Seeds: A Distributed Audiovisual System for Transforming Neural Data

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionGrowing Seeds (2023) explores the transformation of neural activity into sound, image, and movement.
Through fNIRS, brain signals are translated into generative audio, Disklavier piano actions, and holographic LED visuals, forming a recursive performance ecology where cognition and environment continuously reshape each other.

People

Hyo Jee Kang

Korea National University of Transportation

Poster

32. Images Negotiating with Each Other: Māori Conceptualism in a Rule-Based Multi-Agent Drawing Engine

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionAgentic Images is a rule-based multi-agent drawing system in which autonomous agents negotiate territory through five interlocking Māori concepts (mauri, whenua, whanaungatanga, whakapapa, and tikanga), producing emergent composition without training data, LLMs, or diffusion.

People

Roman Mitch

Skills Group

Skills Institute

Poster

33. In-situ Evaluation of Multimodal Telepresence Using Point Clouds and Floor Vibrations at EXPO 2025

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper reports a 70-participant in-situ user study evaluating immersive content delivered via a multimodal telepresence system at the NTT Pavilion, EXPO 2025 Osaka, Kansai, Japan. Fifty general users and 20 visual media experts evaluated three visual stimuli - real-time point clouds, pre-produced volumetric CG, and stereoscopic live-action video - using the Semantic Differential method, combined with floor-based vibrotactile feedback. Point clouds were rated lower in Emotional Response and Immersion than live-action, but achieved comparable ratings in Novelty & Originality, supporting their acceptance as a novel expressive medium. Open-ended responses identified life-sized presentation and a fixed observer-aligned viewpoint as critical factors for co-presence. Floor-based vibrations enhanced spatial reality, while transducer-induced acoustic noise hindered immersion in some cases. These findings, derived from authentic large-scale public exhibition conditions rather than controlled laboratory settings, provide empirically grounded design guidelines for future multimodal telepresence systems.

People

Poster

34. Kaleidoscope of Thoughts: A Participatory Immersive Framework for Visualizing Multilingual Emotional Cognition

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionKaleidoscope of Thoughts is a participatory immersive installation that transforms anonymous multilingual reflections into generative visuals and spatial sound. Presented within a 360-degree projection environment, the work visualizes inner speech, memory, and emotional cognition as a shared audiovisual experience, using real-time media systems to translate private thoughts into collective spatial patterns.

People

Megha Sachdeva

ASU Media and Immersive eXperience (MIX) Center

Poster

35. NHK Data Mashup and Analytic Probe System (NMAPS): A Data Visualization System for Broadcast-Ready Graphics in TV Production

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present NMAPS, an integrated data visualization platform for broadcast journalism. Comprising Digital Earth 4 (DE4) for real-time geospatial visualization and Data Navigator for open-data dashboards, NMAPS delivers a pipeline from data collection to broadcast-quality video output. DE4 serves all 50 NHK regional stations for daily weather and disaster reporting.

People

Satoshi Suzuki

Yuki Kawamura

Akatoki Noboriguchi

Jyunki Yoshii

Taisuke Nakamichi

Rihoko Tsukiyama

36. 'Out of the Box' - Synthesizing Historical Fashion for Virtual Production, XR, and Games via Generative Re-imagination and 4DGS

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a pipeline transforming fragile historical costumes into dynamic digital assets through Generative Re-imagination. Bridging the gap between limited physical access and production needs, our novel method unifies multiple 3DGS models into seamless animated representations. Practical examples include digital actors and animated virtual fashion shows for XR & VP.

People

Moholy-Nagy University of Art and Design

Zsuzsanna Vincze

Moholy-Nagy University of Art and Design

Poster

37. Programmable LED Dance Costumes: Designing Embodied Wearable Technology to Enhance Kinesthetic Expression for Dance Performance

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis creativity-support tool addresses a key gap in dance wearable technology, where most LED costumes are decorative, pre-programmed, or restrictive to movement, through two live-programmable LED costumes and a custom control interface that enable real-time authorship of lighting while preserving dancer mobility and transforming movement into dynamic visual expression.

People

Siddharth Chattoraj

38. Puzzle: A Reflective AI Interface for Convergent Creative Thinking

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionPuzzle is an AI-scaffolded direct manipulation workspace that helps creators synthesize scattered fragments into coherent design directions, pairing a four-quadrant reasoning puzzling with a multi-agent pipeline that surfaces latent themes while keeping every suggestion grounded in the user's own material and thoughts.

People

Poster

39. Revitalizing Heritage Logic: A Procedural Morphogenesis Tool for the Stochastic Evolution of Beijing Palace Lanterns

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis research introduces a procedural framework and a Houdini-based morphogenesis tool that balances "structural genes" with "controlled randomness," facilitating a complete workflow from algorithmic evolution to artistic practice and physical fabrication of Beijing Palace Lanterns while bridging cultural legibility with generative innovation.

People

Birds of a Feather

3D Assets: New features, Tooling, and What Comes Next

10:00am - 11:00am PDT Tuesday, 21 July 2026 Room 518

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Digital Twins

Games

Graphics Systems Architecture

Modeling

Pipeline Tools and Work

Real-Time

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionInteroperable assets are foundational to spatial computing, whether it be representing people, places, or things. This BoF takes a look at some of the interoperable asset work that's gone on between various SDOs in the last year; their ratification status, real-world implementations, available tooling, and sample assets. These are standards that are continuing their development into the next year; this is your opportunity to shape the directions of the standards.

People

Ken Jakubzak

Meta

Bentley / Metaverse Standards Forum

Henrik Edstrom

3D Gaussian Splatting I - Interactive Discussion

Birds of a Feather

3D challenges in .MIL

10:00am - 11:00am PDT Tuesday, 21 July 2026 Room 512

Arts & Design

Modeling

Full Conference Supporter

Full Conference

Experience

DescriptionThis is an informal meet-up for Gov/DoD/Mil artists and storytellers to discuss common challenges in our unique work environments.

The target audience is individuals with .mil, .gov email addresses.

People

Rodney France

USAFWC/A9

Technical Paper

3:00pm - 3:30pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionAfter the summary presentations, attendees will participate in an interactive discussion. Outside the room will be a series of poster boards for authors to gather around with the audience. Authors are invited to bring any material related to their paper that could instigate further conversation such as printouts, posters, demos, or other presentation aids. The interactive discussions provide attendees more interaction with the individual authors.

Technical Paper

3D Gaussian Splatting II - Interactive Discussion

3:00pm - 3:30pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

Technical Paper

3D Generation - Interactive Discussion

11:55am - 12:25pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

Birds of a Feather

3D Jobs Outside of Entertainment - A Panel by The 3D Artist Community

9:00am - 10:30am PDT Tuesday, 21 July 2026 Room 513

Arts & Design

Production & Animation

Animation

Digital Twins

Games

Industry Insight

Full Conference Supporter

Full Conference

Experience

DescriptionEver thought about taking your 3D skills beyond entertainment but had no idea where to start?
Join a panel of working 3D artists who've built careers outside of VFX, gaming, and animation. They'll share how they made the leap into industries like fashion, product visualization, automotive design, motion graphics, and more.

Whether you're curious about a pivot or just want to know what's out there, this conversation will open your eyes to how far your skills can take you.

Come with questions!

People

Michael Tanzillo

Head of 3D Tech Artists & Solution Consultants

Adobe

The 3D Artist Newsletter & Community

Spatial Storytelling

3DGS in Web Gaming: ‘The Shadow of the Czar’

3:00pm - 3:45pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Art

Games

Generative AI

Lighting

Pipeline Tools and Work

Real-Time

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

Description‘The Shadow of the Czar’ is the jazz-infused, Webby-honored noir game by James C. Kane featuring breakthrough use of 3D gaussian splat generation, reconstruction and rendering techniques in the browser. This demo will show how the hit cross-platform web title was developed solo and open sourced in just six weeks.

People

James Kane

jamesckane.io

Poster

4. Computational Design of 3D-Printable Freeform Caustic Surfaces

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis research introduces a novel caustic lens design algorithm and fabrication framework, pairing an inverse design algorithm with accessible desktop 3D printing to enable creators to seamlessly embed custom, irregular, double-sided caustic lenses into freeform physical objects.

People

Shuowen Li

Hong Kong Polytechnic University

The Hong Kong Polytechnic University

Poster

40. Sound Sponges II: Urban Prosthetics and Tangible Urban Interaction for Programmable Acoustic Cities

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce a real-time volumetric acoustic field model that transforms urban noise into a manipulable 3D design medium, enabling simulation and evaluation of spatial interventions (“Sound Sponges”) that reshape city-scale sound distributions through programmable, material-driven attenuation within a digital twin environment.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

University of California, Los Angeles

Poster

41. Struggle of Seeds: Robotic Photography as a Performative Agent

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionStruggle of Seeds is a performance artwork focusing on photography, robotics, and contemporary dance, examining how photographic capture acts as a choreographic agent through a bespoke robot. Photography is positioned not as a representational technique but as an operation of capture, interruption, and appropriation through which power relations are reconfigured.

People

Masaru Mizuochi

Sony Corporation

Creative Computing Institute, University of the Arts London

Shanshan Zhang

University of the Arts London

Vali Lalioti

The Innovation Consultancy

Poster

42. Unveiling Craft Grammar: Transcoding Embroidery into Origami

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce transcoding as a method to extract spatial grammar from embroidery by translating stitches into origami, revealing transferable topological structures through material contrast and enabling process-based representations for digital heritage and generative computational design.

People

Poster

43. Brushes for XR Experiences

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionSilicone brushes designed for XR experiences were evaluated using the Kacho-Zu (Painting of Flowers and Birds) Experience System Using Brushes, suggesting that they have the potential to provide both the sensation of a brush loaded with paint and a favorable drawing experience.

People

Kei Kobayashi

Nagoya City University

Kazuma Nagata

44. CheerleadAR: Pretraining Support for Cheerleading Stunts using Augmented Reality

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper proposes an AR-based pretraining system for cheerleading stunts. Building on a prior VR prototype, the system enables multiple users to virtually experience synchronized stunt movements. It offers a more realistic experience and has potential as a pretraining tool before attempting stunts for the first time.

People

Mizuki Akiyama

Ochanomizu University

Christian Sandor

CNRS

Université Paris-Saclay

Yuki Igarashi

Ochanomizu University

45. Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Procedural Guidance

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionGAIN-AI is a context-aware AI assistant and augmented reality heads-up display designed to support astronauts during lunar extravehicular activities. The system translates dense mission procedures into clear, step-by-step Goal-Task-Verification cards, helping crew members understand what to do, why it matters, and how to confirm successful completion. By grounding a large language model in live telemetry, suit status, task context, and fault-handling data, GAIN-AI can provide timely guidance that adapts to changing mission conditions. Rather than requiring astronauts to search through long procedural documents, the interface presents only the most relevant information at each moment, reducing cognitive load and improving situational awareness. The project explores how AI, augmented reality, and structured procedural design can work together to make complex spacewalk operations more understandable, resilient, and efficient, especially in high-stakes environments where attention, time, and safety are critical to mission success.

People

Rodrigo Gallardo

Qilmeg Doudatcz

Ganit Goldstein

IIkyaz Sarimehmetoglu

Sergio Mutis

Alexander Htet Kyaw

Anita Lin

Clara Emmerling

Berfin Ataman

Skylar Tibbits

46. Design and Evaluation of Mixed Reality Systems for Enhanced Overground Rehabilitation

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis submission presents an embodied mixed reality system for overground lower limb rehabilitation that integrates clinical safety infrastructure, task‑based interaction design, and preliminary patient results, demonstrating strong usability, engagement, and early functional gains, while laying the groundwork for future adaptive difficulty modulation and personalized rehabilitation research.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Jeremy Varghese

State University of New York at Albany

Aishwari Talhan

The Research Foundation at University atAlbany (SUNY)

College of Nanotech, Science, and Engineering, UAlbany

Amy Teale

Saint Peters Health Partners

Thenkurussi Kesavadas

State University of New York at Albany

Poster

47. Fading Peach Blossom Spring: A Perspective-Shifting VR Narrative with Reactive 3D Gaussian Splatting

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present an interactive VR narrative using 3DGS as a reactive medium. By integrating generative AI with a particle-based pipeline, we enable real-time, irreversible environmental dissolution triggered by user touch. This work explores agency-driven storytelling and the emotional impact of intervention through destructive interaction.

People

Sirui Xiao

Communication University of China

Zihan Gao

Communication University of China

Xin Lyu

Communication University of China

Poster

48. Gestural control of quantum information in virtual reality

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis study presents an immersive quantum interface that reimagines the qubit as an interactive, navigable Bloch sphere. Using hand tracking and a Qiskit-driven backend, users manipulate quantum states and execute logic gates in real time, translating abstract quantum computation into an intuitive embodied experience.

People

Hsin-Chia Chang

Hsing-Chen Lang

Ivan C. H. Liu

Min-En Chou

49. GraspAuto: Real-Time Single-Tap Grasp Authoring for VR/AR Experiences

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionGraspAuto is a real-time single-tap grasp generator for VR that synthesizes realistic and diverse hand grasps on novel 3D objects from a single gesture, with no per-grasp motion capture and no manual joint tuning, fast enough to power both authoring tools and live in-headset synthesis.

People

Technical Paper

4D Human-Scene Reconstruction from Low-Overlap Captures

2:10pm - 2:20pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe reconstruct dynamic 4D scenes with multiple people from just 4 sparse cameras with minimal overlap. Our method separately handles backgrounds using video generation and humans using body model priors, then harmonizes the result with a temporally consistent enhancement step, achieving high-quality novel-viewpoint video from practical, everyday camera setups.

People

Minhyuk Hwang

Sangmin Kim

Seunguk Do

Daneul Kim

Jaesik Park

4D Humans - Interactive Discussion

Technical Paper

2:50pm - 3:20pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

Poster

5. Continual Learning 3D Gaussian Splatting under Joint Structural and Illumination Changes via Inverse Rendering

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce a continual learning framework for 3D Gaussian Splatting that simultaneously handles structural and illumination changes. Combining a relightable scene representation with rehearsal-based updates and cross-environment material regularization, our method efficiently refines scenes from local captures while maintaining globally consistent lighting.

People

Poster

50. Prism: A Multimodal XR Assistant for Spatial Imaging Workflows in Interventional Radiology

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionPrism is an XR application for interventional radiology that renders DICOM medical imaging as interactive cross-sectional models and ray-cast volumes within a touch-free, voice-controlled spatial workspace—letting clinicians measure and inspect anatomy without leaving the sterile field, and share the same view with colleagues across Apple Vision Pro headsets.

People

51. See/Saw: Embodied Probing of Vision Transformer Attention in Virtual Reality

Jenny Wang

MedVR

Min Lang

Harvard Medical School

Raul N. Uppot

Harvard Medical School

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionSee/Saw is a VR system that paints a frozen vision transformer's patch groupings and attention onto the 3D surfaces a user aims at in a photorealistic scene, so that turning and walking re-tokenizes the view and the painted regions visibly redraw on the geometry the model saw.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Ziyan Xie

Sihui Lin

52. See What I Hear, Hear What You See: Asymmetric Cross-Modal Play in a Cooperative VR Game

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis study investigates asymmetric cross-modal interaction in a cooperative VR game where sensory roles differ between players, using a two-player prototype showing visual experienced higher engagement while auditory players gained deeper reflection, suggesting such asymmetry creates complementary, distinct experiences and highlights perceptual distribution as a promising design strategy in VR.

People

Nahomi Maki

Keita Kanai

Taruto Fuyama

53. Taste as Form: Real-time Crossmodal Visualization of Eating Experiences in Mixed Reality

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionTaste as Form is a mixed reality system exploring what humans share in how they perceive food. Using AI-based food analysis and sEMG chewing signals, the system maps taste and texture attributes to dynamic visual forms, creating an embodied feedback loop between eating behavior and visual experience.

People

Qingzhu Zhang

University of California Berkeley

Yunting Zhao

Independent Practice

Poster

54. A CG-In-the-Loop Workflow for Designing Multilayer Bubble Display Systems

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a real-time CG-in-the-loop workflow for designing multilayer bubble displays. A single image-derived control stream synchronizes simulation and physical output, enabling rapid iteration without hardware trial-and-error. A five-layer prototype demonstrates parallax and occlusion effects, enabling efficient exploration of volumetric aquatic visuals without full fluid simulation.

People

Honoka Kajita

Akira Nakayasu

55. A Proposal for Simultaneous Multi-User Floor-Based Stereoscopic Imagery

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose a floor projection method enabling multiple users to simultaneously experience individualized anamorphic stereoscopic imagery. By tracking viewpoints, guiding gaze, and dynamically generating projections, users perceive distinct 3D objects while moving, with minimal interference, expanding anamorphic applications to multi-user interactive environments.

People

Nanano Ota

Aichi Institute of Technology

Runa Shimazaki

Aichi Institute of Technology

Shinji Mizuno

Aichi Institute of Technology

Kenji Funahashi

Nagoya Institute of Technology

Poster

56. Enhancing Depth Perception in Stereoscopic 3D and Virtual Reality Media

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis study introduces personalized monocular depth enhancements, such as depth-of-field blur, colour temperature, and saturation modulation, that improve S3D and VR accessibility, effectively raising the performance of stereoimpaired users to levels comparable to those of users with full binocular vision in both passive identification and active navigation tasks.

People

Poster

57. Improving Convergence of Fourier Optical Shading for Nanostructural Diffraction

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionStructural colors from quasi-periodic nanostructures require computationally expensive algorithms. Fourier optical methods for Kirchhoff’s formula achieve real-time performance with photo-realistic rendering. Here, we demonstrate the convergence limits of such methods. Importantly, we propose a Chebyshev approximation approach that avoids the Taylor series. Our method inherently supports generic spectral rendering on-the-fly.

People

Poster

58. Indoor Drone Visual Effects Using LightBenders

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper presents seven visual effects designed for illuminations using a swarm of LightBenders, a drone utilizing an actuated LED rod as its lighting primitive. A Blender add-on empowers artists to design, visualize, edit, and illuminate visual effects for arbitrary words and line drawings using a swarm of LightBenders.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Hamed Alimohammadzadeh

Shahram Ghandeharizadeh

59. Real-Time Light Field Tracing via Display-Architecture Alignment

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper introduces Display-Architecture Alignment to achieve real-time light field rendering on a single consumer GPU. By unifying physical micro-lens geometry with GPU compute scheduling and hardware-adaptive memory layouts, the framework decouples rendering complexity from view count, successfully overcoming traditional compute and memory walls for high-fidelity gigaray-scale tracing.

People

Liulei Zou

Jiangsu University of Technology

Ling Zhu

Unity

Zongyuan Yang

Beijing University of Posts and Telecommunications

Jiaqi Zhao

Material Box

Yongping Xiong

Beijing University of Posts and Telecommunications

Honghui Fan

Jiangsu University of Technology

Poster

6. Distance-Based Iterated Function Systems on Surfaces

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a novel formulation for Iterated Function Systems that allows their generalization to Riemannian domains, enabling the procedural generation of fractal shapes directly on surfaces.

People

Poster

60. Transient Polarimetry

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionCapturing light propagating through time is a photon-starved problem, and the polarization state of light is sensible to noise due to light inefficiency of polarizing optics. Furthermore, imperfect optics and electronics introduce artifacts in the captured signal.

We leverage the structure of transient polarimetry to remove artifacts and reduce noise.

People

Oscar Pueyo-Ciutad

Guillermo Enguita-Lahoz

Diego Gutierrez

61. Wide-Area Stereoscopic Display with Asynchronous Projectors via Gaze-Contingent Localization and Guard Frames

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionA practical method for wide-area binocular stereoscopic display with asynchronous consumer-grade projectors, combining gaze-contingent localization and guard-frame-based virtual synchronization to eliminate hardware synchronization and doubled projector counts.

People

Soga Shirai

Naoki Hashimoto

62. ABCD: Alpha-Composited Block Coordinate Descent

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionAlpha-Composited Block Coordinate Descent enables out-of-core radiance field training by splitting a radiance field scene into spatial partitions, and optimizing one partition at a time while collapsing all frozen partitions into pre-rendered foreground and background images. This reduces GPU memory dependence on total scene size, preserves near-baseline 3DGS quality, and trades scarce VRAM for cheaper RAM or storage.

People

Ka Shiu

Kartic Subr

63. Clustered Codebook Quantization for 2D Gaussian-based Image Compression

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose CGVQ, a K-means-cluster–guided codebook quantization method for 2D Gaussian-based image compression that improves the rate–distortion performance over baseline models.

People

Runze Cheng

Yicheng Zhan

64. Controllable Image Similarity via Factorized Visual Features

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a controllable image similarity framework that decomposes images into semantic and visual factors, enabling flexible similarity definitions via weighting and improving accuracy over holistic methods in creative domains such as illustrations and logos.

People

Sou Tabata

Keiji Kato

Yuto Tamura

Hajime Seino

65. EchoForge: Interpretable Audio-Conditioned Procedural Scene Generation from Spatial Sound

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionEchoForge explores spatial audio as a prior for procedural 3D scene generation, fusing YAMNet semantic labels and first-order ambisonic (FOA) direction estimates into an auditable scene graph that drives Unity layouts, with three recordings showing that discrete sources yield plausible scenes, diffuse ambience degrades predictably, and semantic vocabulary gaps produce transparent failures.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Poster

66. Extending Thread Display with XY Blower Actuation for Controllable Passive Aerial Imaging

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThread Display extends a wind-suspended thread medium into a 2D array actuated by an XY blower on an AxiDraw stage, with servo-steered airflow and Unreal Engine synchronization. Selective thread standing reconfigures where the screen exists in space, enabling depth-aware projection scenes—grounded running characters, floating objects—on one passive medium. This work was supported by JSPS KAKENHI Grant Number JP25K03165.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Tsukasa Ebisawa

Naoki Hashimoto

67. Fast Sampling of Dynamic 360º Environment Maps Using Video Codec Metadata

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce a fast importance sampling method for 360° environment maps in virtual production and VFX, reusing codec coding trees (HEVC, AV1) to build a probabilistic structure that avoids dense CDFs and enables real‑time video‑driven lighting.

People

Jose Aguerre

Evercast

Poster

68. From Virtual Forests to Real Wildlife: Synthetic Non-Radiometric Thermal UAV Data for Animal Detection

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a scalable pipeline for generating annotated synthetic RGB and non-radiometric thermal UAV data, enabling effective sim-to-real wildlife detection, achieving near-parity with real-data models, and improving precision via SAM3-based refinement while revealing non-radiometric variability as the key challenge for robust deployment.

People

Christoph Praschl

University of Applied Sciences Upper Austria, Hagenberg

David C. Schedl

University of Applied Sciences Upper Austria, Hagenberg

Poster

69. GazeFlow: Diverse Driver Gaze Synthesis via Conditional Flow Matching

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionGazeFlow synthesizes diverse driver gaze-head trajectories for digital humans and Euro NCAP 2026 DMS evaluation by anchoring conditional flow matching to a measured human diversity baseline (D_human=1.94, 59,405 pairs), recovering 93% of human variability where a CVAE saturates at 41%, with a sampling-noise knob for controllable fidelity–diversity trade-off.

People

Yonghyun Kim

Electronics and Telecommunications Research Institute (ETRI)

Woojin Kim

Electronics and Telecommunications Research Institute (ETRI)

Hyunsuk Kim

Electronics and Telecommunications Research Institute (ETRI)

Eun Hye Jang

Electronics and Telecommunications Research Institute (ETRI)

Daesub Yoon

Electronics and Telecommunications Research Institute (ETRI)

Poster

7. Fracture-Based Cut Computation for Parametrization

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce a method for cutting manifold surfaces to make them flattenable for parametrization. By optimizing a combined distortion energy and fracture-inspired cut energy on an exploded mesh, we can achieve a target cut length while minimizing distortion. Our method supports application-specific seam weighting and integrates with any parametrization method.

People

Alice Ziyu Wei

Dylan Rowe

Oded Stein

Technion

70. Literature2Heritage: A Retrieval-Augmented Framework for Traceable Image Generation of Heritage Architecture

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionLiterature2Heritage is a retrieval-augmented framework that reconstructs cultural heritage imagery by grounding diffusion model generation in archaeological literature, establishing explicit traceable mappings from every visual element back to its citable source through a dual-tier knowledge base and pixel-level semantic attribution.

People

Yue Hua

School of Design/ Spatial Intelligence and Virtual-Real Fusion Design Laboratory, Shanghai Jiao Tong University

Huaqing Huang

School of Design/ Spatial Intelligence and Virtual-Real Fusion Design Laboratory, Shanghai Jiao Tong University

Poster

71. Procedural Modeling of Wood Decay and Insect Damage for Generating Building Inspection Training Data

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose a procedural pipeline that generates synthetic training images of rare wood damage—white rot, termite tubes, and beetle exit holes—by simulating their underlying biological mechanisms.
A SegFormer trained solely on synthetic data achieves 58.65% mean IoU on real photographs, demonstrating viable sim-to-real transfer.

People

72. Promoting LDR Panoramas to HDRI with Rendering-Space Losses

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a method that restores clipped highlight radiance in HDR panoramas by fine-tuning Wan 2.1 VACE 14B with rendering-aware losses, improving diffuse irradiance and glossy specular image-based lighting quality.

People

Zhengming Yu

73. Radial Residual Frequency: A Semantically Aligned Benchmark and Spectral Detector for AI-Generated Images

Netflix Eyeline Studios

Li Ma

Netflix Eyeline Studios

Mingming He

Netflix Eyeline Studios

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe release a semantically aligned real/synthetic image benchmark and Radial Residual Frequency (rrF), a lightweight spectral metric that captures directional asymmetry in the FFT log-magnitude. A ResNet-50+rrF detector reaches 99.58% accuracy on 4,000 paired images across SDXL, Stable Diffusion 3.5, and GPT-Image 1, substantially outperforming existing detectors.

People

Guang Yang

University of California, Berkeley

Qian Zhang

College of Charleston

Fengchen Liu

University of California, Berkeley

Poster

74. ResonantLoom: Neural Acoustic Rendering for Editable Multi-Entity Video-to-Audio Synthesis

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionResonantLoom, a pioneering AI sound design and editing tool, reframes video-to-audio synthesis as neural acoustic rendering, decomposing visual scenes into independently editable stems via Additive Vector Field Decomposition, achieving a 90% reduction in source leakage and a 7.4x workflow speedup over state-of-the-art baselines while maintaining competitive audio fidelity.

INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION

People

Fnu Hridyanshu

75. SemanticSRJudge: Region-Aware Super-Resolution Diagnosis via Semantic Drift Heatmaps and Perceptual Evaluation

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose SemanticSRJudge, a training-free pipeline that routes a vision-language model to the most distorted regions of a super-resolved image (localised via DINOv2) and judges them at native resolution—rather than scoring the full image, where micro-failures are diluted by intact context. Our key novelty is region-conditioned, dimensional judging: diagnosing what failed and where, instead of collapsing quality into a single scalar. Through a large-scale study spanning four SR architectures, four datasets, both 2× and 4× scales, and thousands of judge calls, we establish three findings. (1) Region conditioning deflates overly optimistic full-image scores on texture and upsampling quality, where small failures hide. (2) We uncover a content-dependent prior-selection rule no scalar metric captures: diffusion priors (SUPIR) dominate at 4× on faces, animals, and indoor scenes, yet hallucinate plausible-but-wrong detail on text and patterns, losing to Real-ESRGAN+. (3) Region conditioning significantly improves alignment with human preference.

People

Poster

76. StableProjectorz: Open-Source, Artist-Driven Texture Synthesis for 3D Assets via Multi-View Diffusion on Consumer GPUs

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionStableProjectorz is a free, open-source desktop tool that lets artists texture 3D models by projecting Stable Diffusion generations onto surfaces via perspective-shifted multi-view conditioning. It features brush-based blending and depth-aware projection masks - running entirely on a single consumer GPU.
StableProjectorz supports several 2D and 3D backends, such as Automatic1111, Forge Webui, ComfyUI as well as 3D generation backends like Trellis.2 and Hunyuan 2.1

People

Igor Aherne

Independent developer

Poster

77. Before We Forget: An Immersive Virtual Reality Exploration Of Historical Displacement Using CAVE2

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionBefore We Forget is a CAVE2 virtual reality experience where users dismantle brutalist 1960s structures and rebuild with indigenous materials, moving through three temporal states of the University of Illinois Chicago campus to confront histories of colonization and urban renewal.

People

Aaqel Shaik

Syed Taha Hasan

Joel Lau Arrieta

Ali Khurram

Hal Brynteson

Grace Spee

Saeed Boorboor

Daria Tsoupikova

Victor Mateevitsi

Argonne National Laboratory

Khin Yuupar Myat

78. Bridging Classroom and Studio: A Hybrid Tangible Multi-Touch Interface for Virtual Production

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe extend the cineDESK virtual production tabletop with a hybrid multi‑touch and tangible 6DoF interface for education. The system reallocates camera control to a physical controller, reduces on‑screen clutter, accelerates layout tasks, and enables more fluid, inclusive collaboration among students with varied technical backgrounds.

People

Poster

79. Clustering Attentional Types in Conditional Automated Driving for Adaptive Take-Over Request Design

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionThis study clusters 93 drivers by pre-take-over gaze and head-movement behavior, identifying three attentional types that reveal a Forward Gaze Paradox and a cognitive-behavioral dissociation undetectable by current gaze-based driver monitoring, providing a foundation for adaptive take-over request interfaces in conditional automated driving.

People

Mi Chang

Electronics and Telecommunications Research Institute (ETRI)

University of Science and Technology

Eun Hye Jang

Electronics and Telecommunications Research Institute (ETRI)

Woojin Kim

Electronics and Telecommunications Research Institute (ETRI)

Jiwoo Han

Electronics and Telecommunications Research Institute (ETRI)

Daesub Yoon

Electronics and Telecommunications Research Institute (ETRI)

Yang Koo Lee

Electronics and Telecommunications Research Institute (ETRI)

Kezia Amanda Kurniadi

Electronics and Telecommunications Research Institute (ETRI)

Poster

8. Helical Box Joints

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce helical box joints, a new class of integral joints that generalizes traditional oblique box joints to support translational, rotational, and twist-in assembly motions, with functional and aesthetic parameters decoupled, and validate the approach through 3D-printed prototypes.

People

Quentin Becker

Maria Larsson

Takeo Igarashi

80. Lattice Musicking: A Collaborative XR Experience for Exploring Musical Structure Through Ratio-Based Lattices

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionLattice Musicking is an XR-based audiovisual system that enables users to interact with rhythm and harmony through lattice structures, supporting spatial audio composition through object manipulation and real-time remote collaboration across MR and VR environments.

People

Ryu Nakagawa

Nagoya City University

Stanford University / CCRMA

Hidefumi Ohmura

Tokyo University of Science

Poster

81. Tangible AI Mind-map: A Graph-Based Interface for Human-AI Brainstorming Using Projection-Based AR, Gesture Recognition and Large Language Models

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe are interested in how AI can participate in creative conversation as a collaborator rather than only as a backend utility. Brainstorming is a useful setting for this question because it is open-ended, often disorganized, and rarely documented in ways that preserve the flow of spoken thought, emerging themes, and shifts in attention. People gesture, point, cluster, and spatially organize ideas, which creates an opportunity for AI systems to leverage embodied and spatial interactions when supporting human-ai co-ideation.

People

Alexander Htet Kyaw

Yifei Li

Jin Gao

82. Tessera: Participation as Cultural Reconstruction Through Confidence-Aware Temporal Rendering

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionTessera is a participatory heritage reconstruction system that maps per-vertex reconstruction confidence to a five-stage visual degradation spectrum in VR, transforming uncertainty into legible rendering that motivates crowdsourced contribution. Validated on Palmyra, Syria, achieving 73 fps on Meta Quest 3 for a 1.8M-triangle multi-era model.

People

Jiawei Tong

University of Liverpool

Shuihua Wang

Xiaoyu Zhang

Royal college of art

Yan Zhao

John Moraros

83. Unfolding Myth in Motion: A Multi-Screen Installation

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionAlt-Mirage is a multi screen installation that stages embodied social deduction among myth guided agents and human spectators. A Supervisor observes global state, generates overlays and replay, and steers pacing indirectly. The work shows how mediation can make embodied AI deception legible, discussable, and open to critique in real time.

People

Baoyang Chen

HKUST

Central Academy of Fine Arts

Yan Liu

Institute of Information Engineering, Chinese Academy of Sciences

Lidong Zhai

Institute of Information Engineering, Chinese Academy of Sciences

Huamin Qu

HKUST

Poster

84. Writing with Piano, Listening with Ink

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionINK SONATA transforms Western classical music into dynamically generated Chinese calligraphy through AI-driven semantic generation and real-time interaction. Reimagining calligraphy as a performative medium, the work uses emotion as a meta-language and invites audiences to experience writing through playing, opening new possibilities for cross-cultural artistic understanding.

People

Jia-Qi Shi

Hong Kong University of Science and Technology, Guangzhou

Troy TianYu Lin

Hong Kong University of Science and Technology, Guangzhou

Zhijun Ma

Hong Kong University of Science and Technology, Guangzhou

Kang Zhang

Hong Kong University of Science and Technology, Guangzhou

Poster

85. A Texture Rendering Method through Control of the Reflection Properties on Resin Surfaces

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose a method to control resin surface glossiness by etching irregular cells whose size and density vary with image tones, enabling reproduction of tonal gradations through reflected light intensity variations.

People

Naoki Kawai

Hirohisa Ota

Ryo Nakamoto

Yasunobu Idei

86. Ghost ReSTIR: Volumetric Resampling with Ghost Vertices in Null-Scattering Space

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionGhost ReSTIR reformulates volumetric ReSTIR in null-scattering primary sample space, eliminating transmittance from the target function for consistent evaluation across all resampling stages. Ghost vertices—auxiliary infinite tails appended after each real vertex—enable well-defined reconnection shifts in dynamic volumes with variable null-vertex counts, improving both quality and performance.

People

Poster

87. Lightweight Attention-based Indirect Illumination

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a lightweight attention-based model for global illumination that combines screen-space G-buffers with reflective shadow map data from light sources, faithfully reconstructing complex indirect lighting effects while generalizing to scenes entirely unseen during training.

People

Wojciech Uss

SungYe Kim

Wojciech Kaliński

Harish Anand

Alexandr Kuznetsov

Rama Harihara

88. OnomatoBridge: Onomatopoeia Translation and Rendering Pipeline in Manga

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionOnomatopoeia in Manga specifically appeals to the audience with its unique visual styles.
vsual onomatopoeia translation requires the clean replacement of onomatopoeia while preserving their visual style.
Existing approaches often produce residual artifacts or style inconsistency.
To approach these problems, we present OnomatoBridge, a filtering pipeline for visual onomatopoeia translation.

People

Takara Taniguchi

89. Pre-Print Visualization of Layer-Induced Appearance Changes in FDM Objects via Differentiable Rendering

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose a method to support visual pre-print inspection of layer-induced appearance changes in FDM 3D-printed objects, utilizing slicer-generated toolpath data. Using differentiable rendering, we optimize an environment map to obtain a lighting environment that makes the layered structure perceptually prominent.

People

Technical Paper

8DNA: 8D Neural Asset Light Transport by Distribution Learning

2:00pm - 2:10pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe pre-bake complex light scattering in 3D assets into neural 8D light transport functions by learning distributions from forward path-traced samples. Unlike previous far-field methods, our representation remains accurate under near-field illumination, while delivering lower variance and faster inference across challenging scenes than path tracing.

People

Liwen Wu

Haolin Lu

Bing Xu

9. Micropolygon Modeling: A New Paradigm for Authoring High-Poly Meshes

Poster

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionMicropolygon modeling is a new approach to authoring high-resolution 3D meshes. Instead of editing individual polygons, artists edit a persistent higher-level structure of regions, boundaries, and points, while the system maintains the underlying triangle mesh automatically. A small set of familiar operations, carving, extrusion, scaling, and slicing, lets meaningful surface regions be created once and reused throughout modeling.

People

Benjamin Mastripolito

Poster

90. Real-Time Ray Tracing of High-Degree Trimmed NURBS via Bounded-Error Bicubic Approximation

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose three algorithmic improvements for ray tracing NURBS geometry, achieving a 2–3× average speedup over prior work and up to 20× on high-degree models, with no noticeable loss of visual fidelity, enabling real-time rendering of industrial CAD models.

People

Maksim Kunts

Institute for Artificial Intelligence, Lomonosov Moscow State University

Ivan Korotaev

Institute for Artificial Intelligence, Lomonosov Moscow State University

Vadim Sanzharov

Institute for Artificial Intelligence, Lomonosov Moscow State University

Sergei Anikin

Lomonosov Moscow State University

Alexey Voloboy

Vladimir Frolov

Institute for Artificial Intelligence, Lomonosov Moscow State University

Poster

91. SceneTrust: Real-Time Confidence-Aware Scene Rendering for Transparent Autonomous Vehicle Decision Visualization in VR

9:00am - 5:30pm PDT Sunday, 19 July 2026 West Hall Lobby

Full Conference Supporter

Full Conference

Experience

DescriptionSceneTrust is a real-time confidence-aware VR rendering pipeline that visualizes autonomous vehicle perception, prediction, and planning decisions through three synchronized layers with physiologically-adaptive scene generation. A pilot study (N=9) demonstrates 62% improvement in mental model accuracy and validated VR-to-real trust transfer on Meta Quest 3 at 120 FPS.

People

Jiawei Tong

University of liverpool

Tieendiesi Manatibieke

Nuova Accademia di Belle

Yan Zhao

Xi'an Jiaotong Liverpool university

Shuihua Wang

John Moraros

Xi'an Jiaotong Liverpool university

Technical Paper

A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry

10:55am - 11:05am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a Bayesian framework for task-specific next-best-view selection in 3D reconstruction. Unlike general uncertainty-reduction methods, we selectively reduce uncertainty only in regions critical to the downstream task via task-specific acquisition functions on posterior distributions over implicit surfaces, achieving superior performance with fewer views across classification, segmentation, and physics simulations.

People

Technical Paper

A Few-Step Generative Model on Cumulative Flow Maps

2:40pm - 2:50pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe propose a unified few-step generative framework based on cumulative flow maps for long-range transport in probability space. By connecting instantaneous updates with finite-time transport, it applies broadly to diffusion and flow models, supports few-step and one-step generation, requires minimal modifications, preserves quality, and reduces inference cost across diverse tasks.

People

Zhiqi Li

Duowen Chen

Yuchen Sun

Bo Zhu

A Generalizable Light Transport 3D Embedding for Global Illumination

Technical Paper

2:10pm - 2:20pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a scalable 3D embedding that learns global illumination directly from 3D scene configurations. This design scales to environments with millions of triangles, enabling the first generalizable GI learning on complex, high-fidelity indoor scenes, far beyond prior limits. It bypasses per-scene retraining and screen-space artifacts to deliver realistic rendering.

People

Bing Xu

Mukund Varma T

Cheng Wang

Tzu-mao Li

Marco Salvi

A Generative Motion Rig for Artist-Driven Motion Authoring

Talks

11:05am - 11:25am PDT Monday, 20 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Dynamics

Games

Generative AI

Geometry

Modeling

Performance

Pipeline Tools and Work

Real-Time

Simulation

Full Conference Supporter

Full Conference

DescriptionRecent breakthroughs in generative modeling enable scaling 3D motion via sparse handles. We introduce the Generative Motion Rig (GMR), a Blender plugin bridging research and production. Through "generative keyframing," artists rapidly author or edit sequences using noise sampling and pose manipulation, streamlining the transition from traditional animation to AI-driven workflows.

People

Jakob Buhmann

Dhruv Agrawal

Dominik Borer

Luca Vögeli

Robert Sumner

Martin Guay

A Hybrid BVH Structure for Interactive GPU Ray Tracing

Talks

11:05am - 11:25am PDT Thursday, 23 July 2026 Room 515 A

Arts & Design

Production & Animation

Research & Education

Animation

Augmented Reality

Dynamics

Games

Geometry

Lighting

Math Foundations and Theory

Modeling

Pipeline Tools and Work

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionChoosing a BVH structure for accelerating ray tracing applications typically involves trading off between BVH build/update speed and BVH traversal speed. We introduce a hybrid BVH structure that combines the strengths of both the standard two-level structure and a monolithic single-level BVH, while minimizing the downsides of either approach.

People

Andrew Bauer

Yining Karl Li

A Hybrid Rendering Approach to Scalable Synthetic Data Generation

Talks

2:40pm - 3:00pm PDT Wednesday, 22 July 2026 Room 515 A

Arts & Design

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Games

Generative AI

Industry Insight

Lighting

Modeling

Physical AI

Pipeline Tools and Work

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a scalable hybrid rendering system that addresses the scarcity of rare training data for autonomous vehicles by automatically compositing radiometrically calibrated synthetic objects into real-world HDR image.

People

Computer Animation Festival

A Journey Through Pages

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionIn a quiet library tucked between memory and imagination, a child meets their future self. Through a poetic dialogue about fantasy, longing, and the beauty of growing up, they revisit the wonder of childhood stories and the dreams that shaped them. A Journey Through Pages is a reflective, hand-drawn short film that gently explores the bittersweet magic of moving forward without letting go of the worlds we once believed in.

People

Iris Wu

Director

Sheridan College

Technical Paper

A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction

2:40pm - 2:50pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionGaussian Splatting struggles with large scenes due to memory limits and chunking artifacts. We introduce "A LoD of Gaussians," a new framework enabling ultra-large scene training and rendering on a single consumer GPU. Through out-of-core streaming and Level-of-Detail, it achieves seamless multi-scale reconstruction without relying on scene partitioning.

People

Felix Windisch

Thomas Köhler

Lukas Radl

Mattia D'urso

Michael Steiner

Dieter Schmalstieg

University of Stuttgart

Markus Steinberger

A MIDI-Controlled Water-Droplet Interface for Generating Droplet Impact Sounds

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThe system is a MIDI-controlled interface that enables musical performance using water droplet collision sounds. It integrates solenoid valves for precise droplet timing and diameter control with tubular resonators for frequency-based pitch modulation. This setup achieves expressive rhythm, volume, and pitch through authentic acoustic sounds generated by actual physical phenomena.

People

Taisei Kato

Tetsuaki Baba

A New Media Techspressionist Architectures Experiment: An AR Mediated Speculative Expression in an Audio/Visual 21st century - LA World

ACM SIGGRAPH 365

3:30pm - 4:30pm PDT Wednesday, 22 July 2026 Room 404 AB

Arts & Design

New Technologies

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Display

Education

Generative AI

Graphics Systems Architecture

Image Processing

Performance

Real-Time

Rendering

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAs part of ACM SIGGRAPH DAC’s host city community outreach initiative, this project expands the New Media Architectures series through a collaborative cultural partnership within the City of Los Angeles and the Los Angeles Center for Digital Art (LACDA). Developed for SIGGRAPH LA 2026, the project positions Los Angeles itself as an experimental civic platform for artistic research, public engagement, and interdisciplinary collaboration across art, science, technology, and urban culture.

This co-curated Augmented Reality experimental exhibition brings together architects, artists, composers, computer scientists, media artists, musicians, designers, and technologists to collaboratively develop responsive site-specific works. By engaging the city's cultural histories and communities, the project transforms LA into a living laboratory.

The exhibition investigates how AI, autonomous systems, algorithmic governance, surveillance infrastructures, and machinic economies are reshaping contemporary urban life locally and globally. Through geospatial interventions and hybrid physical-digital experiences, the project proposes new curatorial and research models that rethink public and private space as an augmented networked fabric for artistic, and performative inquiry.

Framed through the concept of “Techspressionism,” the project explores emerging expressive forms shaped by cinematic culture, computational media, immersive environments, and layered digital realities. Central to this initiative is a dialogue between artists, researchers, and local arts communities exploring how creative practice can critically engage and reimagine the future of urban experience.

This DAC session invites the SIGGRAPH community to explore new collaborative models of cultural expansive production that transform Los Angeles into a distributed platform for collective imagination, experimentation, public discourse, and community-centered technological futures.

People

Gustavo Rincon

Gustavo Rincon

A Nonlocal Monolithic Variational Framework for Free Surface Flows

Technical Paper

11:15am - 11:25am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a unified nonlinear optimization framework that achieves a monolithic coupling of incompressibility, viscosity, and surface tension within a single solver. This first particle-based solver resolves their interdependence via position-based nonlocal viscosity formulations, enhancing stability beyond operator-splitting methods.

People

Shusen Liu

Yuzhong Guo

Lixin Ren

Ying Qiao

Xiaowei He

A Robust and Efficient Intersection Algorithm for NURBS Surfaces: Handling Small Loops and Tangent Intersections

Technical Paper

2:00pm - 2:10pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionThis paper presents a robust and efficient method for computing NURBS surface intersection curves, with emphasis on small loops and degenerate cases. By combining winding number theory with subdivision on the parametric domain, the method reliably detects starting points of all branches, improving topological correctness and computational efficiency in CAD.

People

Jieyin Yang

State Key Laboratory of Mathematical Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences University of Chinese Academy of Sciences

Xiaohong Jia

State Key Laboratory of Mathematical Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences University of Chinese Academy of Sciences

Jieyin Yang

Key Laboratory of Mathematics Mechanization, Chinese Academy Of Sciences; University of Chinese Academy of Sciences

Talks

A Scalable UsdSkel Instancer for Crowds

3:00pm - 3:20pm PDT Monday, 20 July 2026 Petree D

Production & Animation

Animation

Modeling

Pipeline Tools and Work

Simulation

Full Conference Supporter

Full Conference

DescriptionUsdSkelPointInstancer is a new USD schema for crowds that combines packed arrays for agent data with prototypes built from shareable UsdSkel components. The increased speed and reduced memory of the new representation was used successfully to represent large crowds on Walt Disney Animation Studios' "Zootopia 2."

People

Cameron Billingham

Patricio Ricaud Cavazos

Abraham Stolk

Nellie Robinson

Moe El-Ali

Harmony M. Li

A Short Among the Stars: Pipeline Adaptation when Everything is a Volume in Disney's "Versa"

Talks

11:25am - 11:45am PDT Thursday, 23 July 2026 Room 515 A

Arts & Design

Production & Animation

Research & Education

Animation

Augmented Reality

Dynamics

Games

Geometry

Lighting

Math Foundations and Theory

Modeling

Pipeline Tools and Work

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWalt Disney Animation Studios' "Versa" is a beautifully emotional six minute short, where volumes make up everything across both environments and characters. This talk explores how we enabled new workflows and achieved cross-departmental collaboration with Effects to bring this unique short to life.

People

Laura Grondahl

Archana Senthilkumar

Lea Reichardt

A Two-Millisecond Passthrough Headset for Perceptual Studies

Technical Paper

4:15pm - 4:25pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present a nearly perspective-correct video passthrough headset with just 2 milliseconds of end-to-end latency. We use this headset to study perceptual requirements for low-latency passthrough in head-mounted displays.

People

Eric Penner

Josephine D'Angelo

University of California, Berkeley

Clinton Smith

Nathan Matsuda

A Unified Homogenization Framework for Straight- and Curved-Crease Origami Materials

Technical Paper

11:05am - 11:15am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a unified computational framework for numerical homogenisation of straight- and curved-crease origami materials with periodic crease patterns.

People

Centre National de la Recherche Scientifique - Laboratoire d'informatique de l'École Polytechnique (LIX)

Bernhard Thomaszewski

Art Gallery

A Walled City

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionPlease visit our website: https://www.zhangweidi.com/awalledcity
Password for Private Documentation Video: AM3
A Walled City is an interactive, generative monument to memory, density, and collective digital presence. Grounded in the spatial logic, zoning, and aesthetics of Hong Kong’s historical Kowloon Walled City, a self-built, hyper dense, decentralized enclave that grew within a political void from the 1950s to 1993, the artist created a customized multi-agent AI system that transforms participant uploaded images into unique architectural chambers. Each chamber functions as a mnemonic capsule that assembles into an evolving urban interface for non hierarchical collective speculation.

People

Weidi Zhang

A Walled City: An Interactive AI Artwork for Decentralized Urban Memories and Collective Presence

Rodger Luo

Minus AI

Art Paper

2:20pm - 2:40pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Generative AI

Image Processing

Modeling

Pipeline Tools and Work

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionIt proposes a new artistic model of collective virtual presence grounded in historical urbanism and decentralized networks. Drawing from the spatial logic and aesthetic influence of the Kowloon Walled City, the project provides a speculative approach to participatory spatial memory systems through interactive AI art experience.

People

Weidi Zhang

The University of Sheffield

lijiaozi Cheng

Course

A Whirlwind Introduction to Computer Graphics

9:00am - 10:30am PDT Monday, 20 July 2026 Room 515 A

Arts & Design

Gaming & Interactive

Research & Education

Animation

Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionFor a beginner, walking into SIGGRAPH is a very intimidating experience. There is so much to see and so much to do, but everyone seems to be speaking an unfamiliar language. No matter who you are, this course is for you! It will give everyone a background in concepts needed to get more from the conference.

People

Mike Bailey

Oregon State University

Technical Paper

Abstraction in Style: Beyond Texture and Color

9:10am - 9:20am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionArtistic styles often involve shape reinterpretation, not merely a change of surface appearance. Conventional style transfer methods miss this deeper abstraction behavior. We introduce Abstraction in Style (AiS), a two-stage generative framework that learns and transfers style at shape level, beyond texture and colors, enabling more expressive and controllable stylization.

People

Birds of a Feather

Access:VFX Networking + Recruiter AMA

11:00am - 1:00pm PDT Thursday, 23 July 2026 Room 512

Arts & Design

Production & Animation

Research & Education

Animation

Industry Insight

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionACCESS:VFX is a global non-profit of over 70 leading Animation and VFX studios. We focus on actively pursuing and encouraging inclusion, diversity, awareness and opportunity.

Step away from your screens and join Access:VFX IRL! While our monthly virtual networking sessions are great, nothing compares to connecting and engaging face-to-face with our amazing community.

This inclusive space is your opportunity to meet-up, share experiences, and build your network. Plus, we’re hosting an exclusive "Ask VFX Recruiters Anything" session. Bring your questions and get honest, real-world advice on how to stand out and navigate the complexities and challenges of the industry today.

People

Birds of a Feather

2:00pm - 3:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionJoin ACES Technical Steering Committee members and fellow imaging professionals for an open, forward-looking discussion on the digital color workflows. Bring your feedback, challenges, and ideas as we discuss current feature support, cross-application interoperability, and what ACES should tackle next.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Scott Dyer

Academy of Motion Picture Arts and Sciences

ACM SIGGRAPH Award Talks

ACM SIGGRAPH Award Presentations and Talks

3:45pm - 5:45pm PDT Tuesday, 21 July 2026 Room 408 B

Full Conference Supporter

Full Conference

Experience

DescriptionEach year, ACM SIGGRAPH presents nine awards recognizing exceptional achievements in computer graphics and interactive techniques at the ACM SIGGRAPH Conference.

For a list of the awardees, visit: https://www.siggraph.org/awards/

ACM SIGGRAPH 365

ACM SIGGRAPH Cartographic Visualization Birds of a Feather

11:45am - 12:45pm PDT Tuesday, 21 July 2026 Room 404 AB

Research & Education

Education

Scientific Visualization

Full Conference Supporter

Full Conference

Experience

DescriptionThe ACM SIGGRAPH Cartographic Visualization (Carto) session explores how viewpoints and techniques from the computer graphics community can be effectively applied to cartographic and spatial data sets. Speakers demonstrate their latest tools and application efforts.

People

ACM SIGGRAPH 365

Art Gallery

Art Paper

ACM SIGGRAPH Digital Arts Community Roundtables

10:30am - 11:30am PDT Thursday, 23 July 2026 Room 409 AB

Arts & Design

Gaming & Interactive

Research & Education

Art

Full Conference Supporter

Full Conference

Experience

DescriptionArt Community Roundtables for Art Papers, Art Gallery, and Digital Arts Community members. Community members will be invited to join conversations related to the Art Gallery, Art Papers, and Digital Arts Community activities, as well as other themes related to the arts at SIGGRAPH.

People

ACM SIGGRAPH Art Advisory Group

SIGGRAPH 2026

ACM SIGGRAPH Art Advisory Group

SIGGRAPH 2026 Art Papers

ACM SIGGRAPH Pioneers Reception

ACM SIGGRAPH 365

6:00pm - 8:00pm PDT Tuesday, 21 July 2026 Room 409 AB

Research & Education

Industry Insight

Pioneers

DescriptionYearly Pioneers social gathering with light appetizers and a cash bar. No agenda, just schmoozing with old friends and colleagues. Admission by Pioneer membership as printed on your badge.

People

Edward Kramer

SIGGRAPH Pioneers Group

Edward Kramer

ACM SIGGRAPH Pioneers

ACM SIGGRAPH 365

ACM SIGGRAPH: Opportunities and Programs for Educators - Part 1

9:15am - 10:15am PDT Sunday, 19 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Education

Full Conference Supporter

Full Conference

Experience

DescriptionThe kickoff of the 2026 SIGGRAPH Educators Program will include an overview of activities and opportunities with, and sponsored by, the ACM SIGGRAPH Education Committee. Additionally, the winning entries from the SpaceTime competition will be shown along with a screening of the show reel for the 2026 double-curated Faculty Submitted Student Work (FSSW) exhibit. Designed as a way for educators to share their project ideas across schools and disciplines, FSSW is an online archive of assignment and project briefs as well as a curated video emphasizing the variety of student work and schools submitted. The annual exhibition video is a taste of the content available on the Education Committee website and this event showcases and celebrates to the greater SIGGRAPH community the best examples of student work done for projects and assignments for the 2025-2026 school year. Part 2 of this event will begin immediately upon the conclusion of presentations in Part 1.

People

New Jersey Institute of Technology

Director Emeritus and Professor

Associate Professor

Director Emeritus and Professor

Associate Professor

ACM SIGGRAPH: Opportunities and Programs for Educators -– Part 2

ACM SIGGRAPH 365

10:30am - 11:30am PDT Sunday, 19 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Education

Full Conference Supporter

Full Conference

Experience

DescriptionThis session is the second part of the kickoff for the 2026 SIGGRAPH Educators Program and will primarily be the screening of the annual show reel for the 2026 double-curated Faculty Submitted Student Work (FSSW) exhibit. Designed as a way for educators to share their project ideas across schools and disciplines, FSSW is an online archive of assignment and project briefs as well as a curated video emphasizing the variety of student work and schools submitted. The annual exhibition video is a taste of the content available on the Education Committee website and this event showcases and celebrates to the greater SIGGRAPH community the best examples of student work done for projects and assignments for the 2025-2026 school year. NOTE: Part 2 will begin immediately upon completion of other presentations by the ACM SIGGRAPH Education Committee that begins in Part 1.

People

New Jersey Institute of Technology

Director Emeritus and Professor

Associate Professor

Director Emeritus and Professor

Associate Professor

ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies

Technical Paper

2:50pm - 3:00pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionACT is a unified AI framework that effortlessly brings static 3D characters to life. By integrating rigging, skinning, and motion generation into a single diffusion-based pipeline, ACT automatically animates characters of any shape, delivering high-quality, physically plausible motions that overcome the limitations of traditional, multi-step animation workflows.

People

Pengyu Long

ByteDance Games

Weirui Wang

Qingcheng Zhao

ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation

Technical Paper

2:20pm - 2:30pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Rendering

Full Conference Supporter

Full Conference

DescriptionActCam is a zero-shot method providing joint control over camera trajectories and character acting. It integrates into preexisting artistic workflows by leveraging traditional cinematography skills for fine-grained control. Requiring no additional training, the framework avoids costly finetuning and adapts across different backbone architectures.

People

Baptiste Bellot-Gurlet

Kinetix

Technical Paper

Adapting Quality Metrics to Tone Mapping

2:00pm - 2:10pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

DescriptionThis work provides a recipe for adapting existing image/video quality metrics for evaluating tone-mapping algorithms. We demonstrate across multiple datasets that when tone-mapped images and their HDR reference are represented in a perceptually-uniform space, existing metrics such as TOPIQ, DISTS, and ColorVideoVDP outperform tone-mapping-specific metrics, such as TMQI and FFTMI.

People

Kenneth Chen

Dongyeon Kim

Yuta Asano

Alexandre Chapiro

Qi Sun

Rafał Mantiuk

Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation

Technical Paper

9:40am - 9:50am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a motion in-betweening method tailored to stylized keyframe-based animation production. Our Adaptive Interpolation–Synthesis layer dynamically blends learned interpolation with direct pose synthesis, mirroring the animator's workflow. Combined with a domain-based input keypose training schedule, our approach achieves state-of-the-art results and accelerates in-betweening by 3.5× in production workflows.

People

Technical Paper

Adaptive Ray Marching for Rendering Gaussian Process Implicit Surfaces

2:50pm - 3:00pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis paper accelerates Gaussian Process Implicit Surface (GPIS) rendering by introducing an online algorithm for incrementally sampling conditional Gaussian distributions along rays and an adaptive ray marching scheme that minimizes steps. Together, these techniques reduce rendering error by up to 46× at equal time compared to prior methods.

People

Zhiqian Zhou

Dario Seyb

Valve

Have A Sleepover Productions

Computer Animation Festival

Addicted To It

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionAddicted To It follows Dace, who attempts the impossible: a peaceful park walk without his phone. Unfortunately, his phone—Phoney Bunny—has other plans and literally springs to life to win him back. Dace soldiers on, recruiting fellow screen junkies to unplug, while Phoney Bunny chases him like a clingy ex with 100% battery. It’s a fast, ridiculous visual feast with zero solutions—just one simple question: can you survive a 5–10 minute walk without your phone?

People

Director | Producer

Composer | Producer

Birds of a Feather

Adopting OpenUSD and MaterialX in Production Pipelines

3:00pm - 4:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 3

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionPresentations and open discussion about integrating OpenUSD and MaterialX in production pipelines, with successes and failures, possible how-tos.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Paolo Selva

800ProductionsNZ

Technical Paper

ADS: Random Sampling of Occupancy Functions using Adaptive Delaunay Scaffolding

11:25am - 11:35am PDT Monday, 20 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present ADS, a method that delivers both pseudo-random surface samples and isosurface connectivity from occupancy functions, unlike prior approaches that typically provide only one. ADS achieves this with orders of magnitude fewer function evaluations at comparable accuracy than prior approaches, by progressively refining a Delaunay scaffold around the surface.

People

Suzuran Takikawa

Leo Foord-Kelcey

Oliver Oxford

Nicholas Vining

Alla Sheffer

Advances in Real-time Rendering in Games, Part I

Course

9:00am - 12:15pm PDT Tuesday, 21 July 2026 Petree D

Gaming & Interactive

Artificial Intelligence/Machine Learning

Games

Rendering

Full Conference Supporter

Full Conference

DescriptionModern video games employ a variety of sophisticated algorithms to produce groundbreaking 3D rendering pushing the visual boundaries and interactive experience of rich environments. This course brings state-of-the-art and production-proven rendering techniques for fast, interactive rendering of complex and engaging virtual worlds of video games.

This is the course to attend if you are in the game development industry or want to learn the latest and greatest techniques in the real-time rendering domain!

People

Advances in Real-time Rendering in Games, Part II

Michał Olejnik

Activision

Course

2:00pm - 5:15pm PDT Tuesday, 21 July 2026 Petree D

Gaming & Interactive

Artificial Intelligence/Machine Learning

Games

Rendering

Full Conference Supporter

Full Conference

People

Talks

Advancing Large-Scale Water Simulation in Avatar: Fire and Ash

3:45pm - 4:05pm PDT Tuesday, 21 July 2026 Room 403 B

Production & Animation

Research & Education

Animation

Art

Capture/Scanning

Digital Twins

Dynamics

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionIn this talk we discuss the collection of improvements we have made to our in-house water system Pahi to deliver the unprecedented scale and complexity of Avatar: Fire and Ash.

People

Lead FX Supervisor

Panel

Advancing Virtual Production: Technical Innovations and Collaborative Pipelines for Film, TV & Live Events

10:45am - 12:15pm PDT Sunday, 19 July 2026 Room 403 A

Production & Animation

Artificial Intelligence/Machine Learning

Computer Vision

Industry Insight

Lighting

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

DescriptionExploring recent advances in virtual production resulting in higher performance, better data interchange, and realtime VP scalability for VFX supervisors and filmmakers. From lumenAOVs to frame generation with nDisplay and fast rendering Gaussian Splats, speakers discuss the integration of Epic and NVIDIA technologies, technical opportunities, pipeline impacts, and collaborative workflows.

People

Technical Paper

Affine Bodies, Shells & Rods - Interactive Discussion

11:55am - 12:25pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

Birds of a Feather

Agentic Workflows

1:00pm - 2:00pm PDT Tuesday, 21 July 2026 JW Marriott - Plaza 1

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionA participant-driven discussion on leveraging AI agents to enhance studio technology and workflow throughput. The goal is to reduce friction in current established studio pipelines by using AI for intervention, answering questions, and solving 'slow' issues, without requiring the removal or changing of existing pipelines. The discussion will explicitly avoid creative and pixel generation topics, focusing solely on augmenting Studio pipelines.

This is part of a linked series of Technical Pipeline BoFs, covering the Reference Platform, Renderfarming, Cloud, Pipeline, and Storage. Attendees will receive invites to our 'Beers of a Feather' event, the same evening.

People

Technical Paper

AGILE: Hand-object Interaction Reconstruction from Video via Agentic Generation

4:15pm - 4:25pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionAGILE reconstructs 3D hand-object interactions from monocular videos via agentic generation. It produces complete, simulation-ready object meshes and robustly estimates object pose without SfM, enabling accurate and stable results on challenging real-world data.

People

Zhejiang University of Technology

Technical Paper

AGIPC: Adaptive In-Solve Algebraic Coarsening for GPU IPC

9:40am - 9:50am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Geometry

Hardware

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a GPU-friendly adaptive algebraic coarsening method guided by Green strain increments and combined with affine embedding to avoid topological changes and irregular memory access, yielding the first fully GPU-optimized adaptive IPC solver with up to 3× speedup over state-of-the-art GPU IPC while preserving identical visuals.

People

Xuan Wang

Zhaofeng Luo

CMU

Kemeng Huang

AI for Creative Visual Content Generation Editing and Understanding (CVEU 2026)

Art Paper

AI and Agency - Q&A

3:20pm - 3:30pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Capture/Scanning

Computer Vision

Display

Ethics and Society

Generative AI

Hardware

Image Processing

Physical AI

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionAfter all the presentations, attendees are invited to participate in a Q&A.

Course

9:00am - 12:15pm PDT Sunday, 19 July 2026 Room 408 A

Arts & Design

Production & Animation

Art

Computer Vision

Generative AI

Full Conference Supporter

Full Conference

DescriptionThis course introduces a multi-agent framework fusing Generative AI’s creativity with Computer Graphics’ precision. Addressing GenAI’s limitations in data accuracy, we demonstrate how agents orchestrate deterministic rendering (e.g., for charts or spatial logic) to guide video synthesis. Attendees will learn to build systems for controllable, precise cinematic and data storytelling.

People

Zheng Wei

Korean Academy of Sciences and Technology

Yuying Tang

Mia Tang

Anyi Rao

AI for Creative Visual Content Generation, Editing and Understanding

Technical Workshop

9:00am - 12:15pm PDT Wednesday, 22 July 2026 Room 406 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Computer Vision

Generative AI

Image Processing

Full Conference Supporter

Full Conference

DescriptionThe 10th installment of the CVEU workshop series marks a transformative shift toward the Next-Generation Creator-Machine Co-Learning Paradigm. Organized by leading academic researchers and the technical architects behind current video generation models, this workshop explores a future where generative AI evolves from a passive tool into a collaborative partner that internalizes both physical laws and artistic intent. Our primary objective is to bridge the "semantic gap" between raw visual tokens and the sophisticated language of cinema, focusing on how World Models can balance physical factuality with creative license. We will investigate how machine learning translate abstract user intent into precise model behavior, effectively reconstructing traditional production pipelines for professional filmmakers and artists alike. Attendees can expect a high-energy program featuring technical demos of AI-native creative workflows, provocative keynote sessions, and an open "Research-meets-Art" roundtable designed to spark dialogue between model builders and visual storytellers. This forum offers a unique opportunity to engage directly with the creators of the world’s most advanced visual AI systems to define the next era of human-machine synergy in the digital arts.

People

Songlin Yang

Gaurav Parmar

Ozgur Kara

AI in Education: Continuing Conversations on Disruptive Trends

Birds of a Feather

11:00am - 12:00pm PDT Thursday, 23 July 2026 Room 510

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Ethics and Society

Games

Generative AI

Graphics Systems Architecture

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionThis BOF session builds on discussions from the 2025 Educators’ Forum panel, which examined the challenges educators face in addressing key industry trends.

The 2026 session will feature a facilitated discussion among organizers and attendees, revisiting major disruptors and trends in: (1) AI in education, (2) industry readiness and partnerships, and (3) evolving learning modalities.

Organizers will begin by sharing insights from the past year, followed by an interactive dialogue on pedagogical strategies, the integration of AI in classrooms, industry perspectives on academic preparation, and opportunities for continuous learning.

People

Nandhini Giri

Purdue University

Director Emeritus and Professor

University of California, Santa Cruz

Spatial Storytelling

Ai War Cloud Database

10:15am - 11:00am PDT Wednesday, 22 July 2026 Concourse Hall

Arts & Design

Research & Education

Art

Ethics and Society

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAI War Cloud Database catalogues the systems used to make automated decisions in warfare, and it maps where the same types of tools appear in smartphones and popular social platforms. This demonstration presents critical and technical decisions that were hand-in-hand, central to research, information design, and proliferation of the experience.

People

Samir Ghosh

Sarah Ciston

Academy of Media Arts

Stage Session

AI World Models: Where Games, VFX, and AI Collide

10:30am - 11:00am PDT Tuesday, 21 July 2026 West Hall A

Gaming & Interactive

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionWorld models can already simulate environments in real time, making them playable, editable, and generated on demand. Are they the next game engine, the future of VFX, or a new medium that encompasses both? Join the COO of World Labs, NVIDIA's creative technology lead, and the Head Of AI Media at Nebius for a straight-talk look at what's working now, what's still hype, and what studios and toolmakers need to prepare for.

People

Talks

AI, The End of Hollywood, and What Comes Next

4:05pm - 4:45pm PDT Tuesday, 21 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Ethics and Society

Generative AI

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

DescriptionDramatic changes in audience behavior, platforms, and viewing habits combined with runaway production to create an existential crisis in Hollywood, even before the arrival of Cinematic AI. While AI is both an accelerant and a solution, the long-term reality is that the algorithm will transform media as we know it.

People

Charlie Fink

Columnist, Forbes

Adjunct, Chapman U, ASU

Birds of a Feather

AI-Powered Standards: How Khronos Is Building the Future of Graphics

5:00pm - 6:00pm PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Graphics Systems Architecture

Industry Insight

Performance

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionFrom specification authorship to community engagement, AI is reshaping how standards bodies like Khronos operate. This panel brings together Khronos Working Group leaders and industry contributors to explore how AI tools are accelerating standards development, improving documentation quality, and lowering barriers for community participation. Panelists will discuss real-world applications — from AI-assisted spec review and conformance testing to smarter developer outreach and feedback analysis. Attendees are invited to join the conversation and share how AI is influencing their own standards workflows. Come ready to ask questions and help shape what's next.

People

Birds of a Feather

AI3D Frontiers: AI for 3D BOF #4

5:00pm - 6:00pm PDT Tuesday, 21 July 2026 Room 518

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Capture/Scanning

Fabrication

Games

Graphics Systems Architecture

Pipeline Tools and Work

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionYour favorite non-commercial, honestly live-demo-focused BOF continues as a place for polymath hackers, artists, researchers, and independent creators to show what they are actually building — from XR to SOTA gen AI 3D agents to the strange, early, hybrid things that do not yet fit neatly into a paper, product category, or formal session.

Come share what you are working on, compare notes from the frontier, and help define what AI for 3D is becoming.

People

Yosun Chang

AI3D.Foundation

AIMagical

Immersive Pavilion

Allow Me Into Your Dream: Sharing Mixed Realities Through Handshake

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAs mixed reality becomes ubiquitous, we risk a fragmented future where users inhabit isolated worlds. TouchPort-Allow Me Into Your Dream is a multi-person sharing protocol that reprograms handshakes: when two MR wearers shake hands, a portal opens over their clasped hands, letting each peek into the other's world and “allowing” them into their “dreams”.

People

Botao Amber Hu

Reality Design Lab

Yilan Tao

Xi’an Jiaotong-Liverpool University

Yue Li

Bernhard Riecke

Ambient-robust Inverse Rendering using Robot-assisted RGB-NIR Imaging

Technical Paper

9:10am - 9:20am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionThis paper presents an ambient-robust inverse rendering method using robot-assisted RGB–NIR imaging. By combining multi-view RGB images with NIR flash images, we reconstruct accurate geometry and reflectance under multiple lighting conditions. We also introduce a robot-assisted imaging system and multi-view RGB–NIR dataset collected across multiple ambient illumination settings.

People

Technical Paper

AMOR: Airborne Motion Reconstruction via Homotopy-Aware Trajectory Optimization

3:55pm - 4:05pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionExisting Human-Mesh-Recovery methods struggle with dynamic airborne motions, often producing unstable and unrealistic results. We present a refinement approach that enforces physical consistency by selecting reliable motion segments, applying homotopy-aware trajectory optimization. Experiments on in-the-wild and challenging videos show improved realism and stability over prior methods.

People

Chanha Kim

Jungdam Won

An Artist-Friendly Albedo Approximation for Transmissive Materials

Talks

10:00am - 10:20am PDT Sunday, 19 July 2026 Room 403 B

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Computer Vision

Digital Twins

Education

Games

Image Processing

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionTransmissive materials are difficult to parameterize in an artist-friendly way. This talk presents a practical albedo approximation derived from a simplified Kubelka–Munk model. Using thin- and thick-layer reflectance, absorption is recovered in closed form, avoiding iterative fitting and enabling efficient, intuitive control for real-time rendering applications.

People

Artem Kryzhanovskyi

Torn Banner Studios

Course

An Introduction to Neural Shading

9:00am - 12:15pm PDT Sunday, 19 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Games

Math Foundations and Theory

Rendering

Full Conference Supporter

Full Conference

DescriptionLearn neural shading from the ground up. This hands-on course teaches attendees to build and train MLPs directly in Slang shaders, leverage GPU tensor cores for hardware acceleration, and implement neural materials — transforming complex visual phenomena into compact, high-fidelity learned representations.

People

Course

An Introduction to Quantum Computing

3:45pm - 5:15pm PDT Sunday, 19 July 2026 Room 515 A

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Computer Vision

Games

Generative AI

Image Processing

Math Foundations and Theory

Simulation

Full Conference Supporter

Full Conference

DescriptionQuantum computing is a radically new and exciting approach to programming. By exploiting the unusual behavior of quantum objects, this new technology invites us to re-imagine the computer graphics methods we know and love in revolutionary new ways. This course is math-free and requires no technical background.

People

Andrew Glassner

Consultant

Course

An Introduction to the Fourier Transform

3:45pm - 5:15pm PDT Thursday, 23 July 2026 Room 515 A

Production & Animation

Research & Education

Audio

Computer Vision

Education

Image Processing

Math Foundations and Theory

Modeling

Rendering

Scientific Visualization

Full Conference Supporter

Full Conference

DescriptionThe Fourier Transform is fundamental to computer graphics, explaining topics from aliasing and sampling to image compression and filtering. This friendly course explains the principles in words, pictures, and animation, rather than math. The concepts are the important thing. We show that they are comprehensible, useful, and beautiful.

People

Andrew Glassner

Consultant

Birds of a Feather

ANARI in Action: Open Rendering for Visualization, Simulation, and Discovery

11:00am - 12:00pm PDT Tuesday, 21 July 2026 Room 518

New Technologies

Research & Education

Digital Twins

Graphics Systems Architecture

Hardware

Industry Insight

Performance

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionANARI is helping make advanced rendering more accessible by decoupling scene description from rendering implementation, enabling developers to take advantage of modern visualization technologies without deep graphics expertise. Join the Khronos Group and the ANARI community for an interactive look at the latest advances in ANARI, including new capabilities, tooling, real world adoption, and integration across scientific visualization, simulation, digital twins, HPC, and industrial workflows. Bring your questions, share your experiences, and help shape the future of open, scalable rendering.

People

Jefferson Amstutz

National Institute of Standards and Technology (NIST)

Bill Sherman

Birds of a Feather

ANARI: Advancing Open Rendering Standards

11:30am - 12:00pm PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

New Technologies

Research & Education

Digital Twins

Graphics Systems Architecture

Hardware

Industry Insight

Performance

Pipeline Tools and Work

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionGet the latest updates directly from the Khronos ANARI Working Group as the ecosystem continues to expand across visualization, simulation, engineering, and high-performance computing. This session will cover recent technical progress, roadmap discussions, interoperability efforts, implementation updates, and opportunities for community participation. Learn how ANARI is evolving to support modern rendering workflows, scalable deployment across diverse hardware and software environments, and closer integration with adjacent Khronos technologies. Join the discussion, connect with contributors, and hear what is next for open, portable rendering standards.

People

National Institute of Standards and Technology (NIST)

Spatial Storytelling

Ancestral Craft and Emerging Technologies: Designing Futures from Place

1:00pm - 1:45pm PDT Tuesday, 21 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

Research & Education

Art

Ethics and Society

Fabrication

Real-Time

Robotics

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThis talk presents a place-based approach to designing interactive systems that combine ancestral craft and emerging technologies. Through XR installations and robotic artworks developed in the Amazon rainfores, it shares methods for building non-generic futures grounded in local knowledge, material practices, collaboration and real-time graphics.

People

gabriela bila advincula

Media Lab, Massachusetts Institute of Technology (MIT)

Jonny Cohen

Media Lab, Massachusetts Institute of Technology (MIT)

Technical Paper

AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation

11:25am - 11:35am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionAniGen generates animatable 3D assets from a single image by jointly producing geometry, skeletons, and skinning weights. Its unified S³ field representation enables consistent, high-quality rigged asset creation across diverse categories, including animals, humans, cartoon characters, and articulated objects.

People

Yi-Hua Huang

Zi-Xin Zou

Yuting He

Chirui Chang

Cheng-Feng Pu

Ziyi Yang

Animating Engagement: Connecting Technology, Artistry, and Purpose in a Small Public University

Educator's Forum

4:05pm - 4:25pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

Research & Education

Animation

Art

Education

Games

Scientific Visualization

Full Conference Supporter

Full Conference

Experience

DescriptionThis talk presents four project-based learning experiences from a small public university animation program, demonstrating how connecting technology, artistry, and purpose fosters student growth and engagement. Through classroom, collaborative, and community-based projects, the talk offers transferable strategies for supporting diverse student populations in evolving creative fields.

People

Damian Thorn-Hauswirth

East Stroudsburg University

Talks

Any Representation, Any Hardware, All Interactions: Accelerating Interactive Prototypes Over Cutting Edge AI & 3D Research

3:00pm - 3:20pm PDT Sunday, 19 July 2026 Room 408 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Games

Generative AI

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionThis talk introduces a new public library, designed for rapid prototyping of interactive Web interfaces over a large class of emerging technologies in 3D representations and AI. We base our design on first-hand experience in developing multiple interactive tools presented at SIGGRAPH as technical papers, Real-Time Live presentations, and Labs.

People

Maria Shugrina

Archiving Media Art and Preserving Obsolete Technologies

Computer Animation Festival

Apart

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionAmid the harsh realities of South African apartheid, two boys—Themba and Joel—form a dangerous friendship. As hate and fear threaten to pull them apart, their bond faces its greatest challenge in the form of a life-saving gesture. Through their eyes, we glimpse a moment of innocence—where hope, empathy, and understanding still feel possible.

People

Pola Maneli

Head of Festivals & Distribution

Social Popcorn Films

Birds of a Feather

3:30pm - 5:30pm PDT Thursday, 23 July 2026 Room 512

Arts & Design

Gaming & Interactive

Research & Education

Art

Augmented Reality

Capture/Scanning

Digital Twins

Education

Hardware

Pipeline Tools and Work

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionHow do museums, archives, and libraries steward media artworks built on obsolete or rapidly aging technologies? From CD-ROMs and Flash to early VR headsets, custom hardware, and platform-dependent installations, much of recent media art history runs on systems no longer manufactured or supported. This Birds of a Feather, convened with the LA Media Art Archives Network, brings together archivists, conservators,curators, artists, and technologists to share institutional approaches. Topics may include emulation, migration, documentation, artist interviews, exhibition and archival standards, and the realities of long-term stewardship of media art. Come share challenges and solutions from your own practice. All levels welcome.

People

Art Gallery

Are We Gazing at the Same Moon?

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionAre We Gazing at the Same Moon? Do we observe things within the same time and space?
The artwork established a moon-gazing ritual that re-imagines the moon as a concurrent presence across parallel realities, questioning the relationship between personal memory and collective memory. Challenging the process of "Lunar Mosaic" by reversing the process and expanding image segments of the collaged moon with generative AI, it questions the notion of a singular, unified human experience of moon-gazing. The project spans various forms, including audio-visual works, sculpture, and public installation.

People

Industry Session

Arm Create - The New Arm Developer Experience

9:00am - 3:00pm PDT Monday, 20 July 2026 Room 308

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Computer Vision

Games

Generative AI

Graphics Systems Architecture

Hardware

Industry Insight

Lighting

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin Arm to build, experiment, and bring ideas to life at Arm Create at SIGGRAPH 2026.

Neural graphics on mobile are rapidly moving from research into real-world development workflows. At Arm Create Dev Day at SIGGRAPH, developers can explore what that means in practice. Bringing together developers, researchers, and ecosystem partners, the event features technical talks, guided demonstrations, and direct access to Arm experts working at the intersection of graphics, AI, and mobile development.

Attendees will experience Neural Dawn, firsthand and learn how to start building with Neural Graphics today: From integrating neural rendering techniques into existing pipelines to preparing ML + GPU workflows for next-generation mobile hardware.

Arm Create Dev Day showcases what developers can build now and how upcoming Arm technologies will expand future possibilities. The conversation continues throughout SIGGRAPH with additional demos, meetings, technical sessions, and stage presentations throughout the week.

People

Educator's Forum

Art + Code: Case Study in Expanding Access with p5.js

11:05am - 11:25am PDT Wednesday, 22 July 2026 Room 501 ABC

Gaming & Interactive

New Technologies

Research & Education

Augmented Reality

Digital Twins

Education

Games

Image Processing

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWidely used for making and teaching algorithmic art, p5.js prioritizes access and expressiveness. What impact does p5.js have on students? This presentation reflects on an educator program that grounds web-based interactive graphics in students' contexts, expanding imagination of what is possible with resources at hand, and suggesting new professional possibilities.

People

Alex Avila

Los Angeles Unified School District

Xin Xin

Roxana Hadad

Kit Kuksenok

Art Gallery and Art Papers Awards Gathering

Art Gallery

Art Paper

3:00pm - 4:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Research & Education

Art

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

Experience

DescriptionWelcome to the Art Gallery and Art Papers Contributors from the Chairs, and announcement of the Best in Show awards for those programs. Acknowledgement of the Distinguished Artist Award winner, and recognition of the contributions of the year-round Digital Arts Community (DAC).

People

Articulate That Object Part (ATOP): 3D Part Articulation from Text and via Motion Personalization

Birds of a Feather

Art in the Time of A.I.

2:00pm - 3:00pm PDT Wednesday, 22 July 2026 Room 510

Arts & Design

Art

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

Experience

DescriptionA discussion about ML/AI technology from an artist's perspective. Some of the issues that exist and where the new technology can help or hinder. Ultimately we will have to ask: what;s art, who;s an artist, and what's good/bad art? How does the use of ML/AI help or hinder the goal of making good art? Are we seeing an exciting new development in art or the downfall of creativity? Let's discuss: Not to convince others to think like we do but to learn from different points of view.

People

Sunil Rampersad

LA ACM SIGGRAPH

Technical Paper

11:35am - 11:45am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present a few-shot method for articulating static 3D objects using text-guided motion personalization. Leveraging diffusion models, we generate plausible part motions and adapt them to input objects via image prompting. Differentiable rendering with score distillation transfers multi-view motion into 3D, enabling optimization of articulation parameters under piecewise rigidity assumptions.

People

Aditya Vora

Sauradip Nag

Kai Wang

Hao (Richard) Zhang

Aditya Vora

ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models

Technical Paper

11:45am - 11:55am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionArtiFixer enhances and extends 3D reconstructions efficiently and scalably. Given an initial reconstruction and reference views, it autoregressive generates novel content consistent with existing observations. ArtiFixer can produce hundreds of novel views in a single inference pass or serve as pseudo-supervision to improve the underlying 3D reconstruction.

People

Tianchang Shen

Asiagraphics Workshop on Neural Graphics Processing

Technical Workshop

9:00am - 12:15pm PDT Sunday, 19 July 2026 Room 406 AB

New Technologies

Research & Education

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionNeural graphics is transforming how we create, represent, and interact with visual content. This workshop brings together leading researchers across geometry, rendering, generative modeling, and embodied AI to present a unified view of this rapidly evolving field.Through a curated sequence of invited talks, the program will guide attendees from geometric foundations and 3D generation to neural rendering, real-time techniques, physics-aware reconstruction, and interaction with the physical world.

The primary objective is to explore how neural representations and generative models can be integrated with classical graphics pipelines to enable more scalable, controllable, and physically grounded visual computing. The workshop will feature the technical presentations, encouraging active engagement between speakers and attendees. Participants can expect lively exchanges, opportunities to ask questions, and insights into emerging research directions.

Designed for researchers, practitioners, and students in graphics, vision, and AI, this workshop offers a concise yet comprehensive overview of neural graphics and its future trajectory.

People

Young J. Kim

Ewha Womans University

HKUST

Takeo Igarashi

Institute of Computing Technology, Chinese Academy of Sciences

Stefanie Zollmann

Aarhus University

Lin Gao

Hao (Richard) Zhang

Qixing Huang

Ravi Ramamoorthi

Mohamed bin Zayed University of Artificial Intelligence

Lingqi Yan

Lingjie Liu

Srinath Sridhar

Assets in Motion (AIM) - Injecting life into a static and linear asset building process

Dinesh Manocha

University of Maryland

Talks

9:20am - 9:40am PDT Sunday, 19 July 2026 Petree D

Production & Animation

Animation

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

DescriptionThis talk introduces Assets in Motions (AIM) at Sony Pictures Imageworks. AIM is a strategic approach, designed to move character designs into well rounded production ready assets in a more cost effective and collaborative way.

People

Hans Heymans

Chris Logan

Brian Cohen

ASWF Diversity & Inclusion Working Group

Birds of a Feather

12:00pm - 1:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Animation

Diversity, Equity and Inclusion

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionThe Diversity & Inclusion WG at the Academy Software Foundation breaks down barriers to access and increases connections among participants in the Foundation’s projects, community, and the VFX & Animation industry. If you are passionate about the Entertainment industry and looking for a way to get involved, please consider attending! Our group members consist of engineers, students, faculty, and more. We'll provide group updates as well as save time for community discussion.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Carol Payne

Academy Software Foundation

Birds of a Feather

ASWF Machine Learning Working Group

11:00am - 12:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 3

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionUpdates from the ASWF Machine Learning Working Group. Ongoing progress on the DNA development and feedback from early adopters. New initiative for mutual learning sessions on the topics of interest in the AI/ML domain in VFX/Animation industry.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Tommy Burnette

ILM

Technical Paper

ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation

2:20pm - 2:30pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionATGS is a volumetric video reconstruction method that handles long sequences with complex motions and supports rendering from arbitrary viewpoints, enabling immersive experiences.

People

Jiahao Wu

School of Computer Science, Peking University

School of Computer Science, Peking University

Jie Liang

Ronggang Wang

Atmospheric Haptics: Rendering Airflow and Temperature as Tactile Fields for Interactive Experiences in Virtual Reality

Pengcheng lab

Technical Paper

4:15pm - 4:25pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Fabrication

Haptics

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionAtmospheric Haptics treats airflow and temperature as programmable, non-contact tactile fields for VR. Four perceptual primitives—Intensity, Temperature, Spatiality, and Dynamics—drive a three-layer rendering pipeline implemented in a handheld prototype. A user study confirms enhanced realism, improved navigation precision, and convincing wetness illusions without liquid contact.

People

Shengyi Zhan

School of software technology, Zhejiang University

Zhejiang Key Laboratory of Intelligent Systems and Equipment for Digital Creativity,Hangzhou,Zhejiang

Xueting Wu

College of computer science and technology, Zhejiang University,Hangzhou, Zhejiang

Zhejiang Key Laboratory of Intelligent Systems and Equipment for Digital Creativity,Hangzhou,Zhejiang

Ning Zou

College of computer science and technology, Zhejiang University,Hangzhou, Zhejiang

Future Design Laboratory, Innovation Centre of Yangtze River Delta, Zhejiang University，Jiaxing,Zhejiang

Technical Paper

AtomSlicer: Constant-Thickness Field-Aligned Non-Planar Slicing and Continuous Toolpaths for FFF

3:45pm - 3:55pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionAtomSlicer is a 3D printing method for fused filament fabrication that generates non-planar layers and continuous toolpaths aligned with user-defined fields. It enables better control of layer orientation, constant thickness, and near-continuous deposition, helping improve print quality, reduce interruptions, and support advanced multi-axis fabrication.

People

Giovanni Cocco

Vincent Belle

Eric Garner

Sylvain Lefebvre

Xavier Chermain

Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing

Technical Paper

4:15pm - 4:25pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Games

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionAudio-Omni is the first unified framework for multi-modal audio generation and editing across sound, music, and speech. By combining a frozen multimodal language model with a trainable diffusion transformer, it achieves state-of-the-art performance on multiple benchmarks while exhibiting remarkable inherited capabilities.

People

Zeyue Tian

Binxin Yang

Tencent

Zhaoyang Liu

Jiexuan Zhang

Ruibin Yuan

Hubery Yin

Tencent

Qifeng Chen

Yike Guo

Stage Session

Augmented, Not Automated

2:00pm - 2:30pm PDT Wednesday, 22 July 2026 West Hall A

Gaming & Interactive

New Technologies

Production & Animation

Artificial Intelligence/Machine Learning

Generative AI

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionGenerative AI does not require creative studios to throw away decades of tools, talent, and pipeline investment. The bigger opportunity is augmentation, not automation: keep the tools artists already know, keep the artists in creative control, and add agents as helpers inside the existing pipeline to take on the repetitive and technical work. This session shows how WWT, NVIDIA, and Cisco make that hybrid pipeline real and safe inside a real production stack, so AI accelerates the creative work without replacing the creator at the center of it.

People

Kyle Lindsey

World Wide Technology

Rick Champagne

Autodesk Vision Series | A Small Team’s Journey to a VES Award-Winning Animated Film

Industry Session

1:15pm - 2:00pm PDT Wednesday, 22 July 2026 Petree C

Production & Animation

Animation

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionMeet the young filmmakers behind Azimuth, a graduation short that went on to win the 24th Visual Effects Society Award for Outstanding Student Project, recognized for its artistry and innovation in animation.

At a time when conversations around AI and humanity are everywhere, the film tells a deeply human story, asking: if technology could recreate someone you love, would it ever truly be enough?
The young filmmakers will share how trust, problem-solving, and a shared love of storytelling helped them create something they never imagined possible together, and how they used Autodesk Maya and Arnold to layout, animate, and render the film under a tight timeline and with limited resources.

People

Director

Industry Session

Autodesk Vision Series | AI for Spatial Storytelling: Going Beyond Generation with 3D World Models

12:00pm - 12:45pm PDT Wednesday, 22 July 2026 Petree C

New Technologies

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Generative AI

Physical AI

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionDiscover how 3D world models are poised to transform animation and visual effects by moving beyond visual generation toward systems that can understand, simulate, and reason about space and time. In this panel, Nikola Todorovic, Co-Founder of Wonder Dynamics, an Autodesk company, and Ben Mildenhall, Co-Founder of World Labs will explore why spatial intelligence and simulation matter for the next generation of creative tools. The conversation will connect long-term research ambitions with real-world production workflows.

People

Industry Session

Autodesk Vision Series | AI in the Production Pipeline: A Conversation with Cinesite's CTO

1:15pm - 2:00pm PDT Tuesday, 21 July 2026 Petree C

New Technologies

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin Cinesite CTO Michele Sciolette for a fireside chat with Kamal Mistry, Sr. Director of Product for Autodesk Media & Entertainment, on how one of the world’s leading animation and VFX studios are approaching AI in production. The conversation will explore where AI can remove friction from creative workflows, how teams evaluate emerging tools for real pipeline use, and what it takes to introduce new capabilities without disrupting artists’ craft, collaboration, or creative control.

People

Industry Session

Autodesk Vision Series | Animating a Multiverse of Horror for Marvel Zombies

2:30pm - 3:15pm PDT Wednesday, 22 July 2026 Petree C

New Technologies

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionInside the making of Marvel Zombies, Stellar Creative Lab reveals the animation pipeline behind Marvel’s darkest animated universe yet. From eerie environments to stylized characters, discover the end-to-end production pipeline behind the #1 Disney+ series – spanning asset creation, layout, animation, lighting, lookdev, and final rendering for a fast-paced episodic workflow.

Learn how the team used Maya for layout and animated performances, Arnold to achieve the show’s stylized horror look through toon shading, and Flow Production Tracking (formerly ShotGrid) to connect artists, assets, and production data across the studio. And discover how OpenUSD helped unify the pipeline, streamline collaboration, and support scalable production across the studio.

Alongside exclusive production insights from Marvel Zombies, the team will discuss how Autodesk’s connected creative ecosystem enabled an artist-friendly workflow built for modern animated storytelling — and how emerging AI-powered workflows may help shape the future of animation production.

People

Industry Session

Autodesk Vision Series | Animating Creatures of the Upside Down with Wētā FX: The Creepy Realism of Stranger Things Season 5

9:30am - 10:15am PDT Tuesday, 21 July 2026 Petree C

Production & Animation

Animation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionIn this talk, Dave Clayton, five-time Academy and BAFTA awards-nominated Animation Supervisor at Wētā FX, will break down some of the techniques used to imbue the creatures and characters of Stranger Things with a new level of creepy realism. Coming on board for the iconic show’s final season, Wētā FX contributed more than 1,100 shots across all eight episodes, for which they received 4 VES nominations.

Starting with Vecna, Dave will review how the team built the villain on concept art from the client, and extended his look and build from prior seasons. From his deadly vines coiling and extending from within his body, to the surprising methods used to arrive at Vecna's ‘charred’ makeover.

He’ll also explain the process of bringing the Demogorgons and Demodogs to new scary-real creative heights though the use of mocap, rag-doll dynamics, muscle simulations and keyframe animation — making them feel a natural part of the Stranger Things creature menagerie.

Finally he’ll dive into the team’s work on the ever-looming Mindflayer: how they animated continuous action to help bring the grand battle finale to a pulse-pounding climax, while crafting its motion to reinforce its scale, weight, and terror. This is a talk that any fan of cutting-edge animation and creature work, or of Stranger Things, shouldn't miss!

People

Dave Clayton

Wētā FX

Industry Session

Autodesk Vision Series | Animating Weapon Skins for VALORANT with Riot Games

9:30am - 10:15am PDT Wednesday, 22 July 2026 Petree C

Gaming & Interactive

Animation

Games

Real-Time

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionPlayers spend hours unlocking the next weapon skin. Now, see firsthand the hours that go into creating those prized skins for VALORANT, Riot Games’ award-winning first-person tactical hero shooter game. Senior Animator, Brendan Russert, shares what it takes to create gun skin animations that feel sharp, unique, and worthy of a clutch moment. He'll cover the artistic decisions behind expressive weapon motion, the gameplay and technical limitations behind these animations, practical Maya tips and tricks, and how those assets make their way into the engine.

People

Brendan Russert

Riot Games

Industry Session

Autodesk Vision Series | Clumsy, Deadly, Unforgettable: Creating the Rad Roach Massacre in Fallout Season 2

2:30pm - 3:15pm PDT Tuesday, 21 July 2026 Petree C

Production & Animation

Animation

Lighting

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin Refuge VFX's founder Fred Ruff and Lead Look Development Artist Stephen Lauser as they break down the creation of the rad roach massacre sequence from Fallout Season 2. From early creative challenges and budget-driven decisions to creature animation, environmental interaction, and final compositing, we'll reveal how a swarm of giant insects became one of the sequence's most memorable and terrifying moments. Through behind-the-scenes footage and shot breakdowns, you'll see how the team transformed clumsy creatures into deadly predators while balancing artistic goals with production realities.

People

Industry Session

Autodesk Vision Series | Crafting Characters Beyond the Reef: Translating Moana’s Animated World into Live Action with ILM

3:45pm - 4:30pm PDT Tuesday, 21 July 2026 Petree C

Production & Animation

Animation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin Industrial Light & Magic Animation Supervisor Maia Kayser for a behind-the-scenes look at the character animation of Disney’s live-action Moana. This presentation explores the technical and artistic challenges of translating the beloved animated world into a photorealistic cinematic experience – crafting digital characters and performances that are both physically grounded and emotionally expressive.

People

Maia Kayser

ILM

Industry Session

Autodesk Vision Series | How to give soul to a faceless alien, question? Animating Rocky in Project Hail Mary with Framestore

10:45am - 11:30am PDT Tuesday, 21 July 2026 Petree C

Production & Animation

Animation

Performance

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionAt the core of Project Hail Mary is an unlikely friendship between an astronaut, Grace, and a faceless alien, Rocky. In this presentation, VFX Supervisor Bob Winter and Animation Supervisor Aulo Licinio break down Framestore’s collaboration with directors Phil Lord and Chris Miller to deliver the emotional heartbeat of the story.

Bringing Rocky to life meant inventing a completely unique physical language for a creature with no eyes, no face, and no human expressions. The team will detail how they navigated the unique challenges of controlling a five-legged anatomy, turning strict biological constraints into endearing character quirks.

Discover how Framestore blended cutting-edge keyframe animation with physical on-set puppetry to build a tactile, believable connection between the two leads, and see if you can spot where the puppet ends and the digital animation begins.

People

Industry Session

Autodesk Vision Series | Not Just Big, Alive: The Animation of Kong in Monarch Season 2

10:45am - 11:30am PDT Wednesday, 22 July 2026 Petree C

Production & Animation

Animation

Capture/Scanning

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionIn Monarch: Legacy of Monsters Season 2, Rodeo FX’s animation team faced a massive challenge: make a 300-foot titan feel like a character. Kong had to emote and move with the weight of something real, not just big.

Animation Supervisor Christophe St-Pierre Paradis walks through the creative and technical process behind Kong's performance in Autodesk Maya, from the motion capture sessions that formed the foundation of his movement, to the animator-driven refinement that transformed raw mocap data into a creature performance with genuine scale and emotional presence. The talk covers locomotion at an impossible scale, fight choreography rooted in intention, the micro-movements that give a giant an inner life, and the pipeline realities of preserving a performance through fur, cloth, and simulation.

People

Christophe St. Pierre Paradis

Rodeo FX

Industry Session

Autodesk Vision Series | What's Next for Animation at Autodesk

12:00pm - 12:45pm PDT Tuesday, 21 July 2026 Petree C

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionCharacter animation workflows are evolving rapidly, creating new opportunities for artists to create more easily, explore ideas, and stay focused on performance and storytelling. Join Autodesk’s Animation and Research teams for an inside look at what’s next in animation at Autodesk and the tools we're building to give you more freedom to create the way you want to create.

Through demos and research previews, you'll see new AI workflows for motion generation, alongside new approaches to story development and planning. You'll also see how Autodesk is building more flexible workflows that support artist choice, control, and interoperability.

People

Technical Paper

Autoregressive B-Rep Shape Generation with Parametric Surfaces

10:55am - 11:05am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionParaCAD is a point-cloud-conditioned autoregressive framework for B-Rep generation that directly predicts native parametric surface types and continuous parameters via a surface-centric tokenization, preserving CAD semantics and downstream editability beyond grid/point-based representations.

People

Dafei Qin

Rui Xu

Zeyu Shen

Kaichun Qiao

Hongyang Lin

Qixuan Zhang

Huaijin Pi

Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

Technical Paper

2:50pm - 3:00pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionARDY is a real-time autoregressive diffusion model for interactive 3D human motion generation. Utilizing a novel hybrid motion representation, ARDY empowers users to interactively synthesize high-fidelity animations directed by dynamic text prompts and flexible spatial constraints, such as full-body keyframes, trajectories, and end-effector joints.

People

Technical Paper

Autoregressive Modeling of Film with Applications in Video Montage

2:40pm - 2:50pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Lighting

Full Conference Supporter

Full Conference

DescriptionThis work introduces an autoregressive transformer designed for video montage, transforming raw footage into cinematic sequences. We train it on large corpora of movies to learn film grammar. Instead of generating pixels, we introduce a footage-constrained decoding algorithm to select shots from the input raw footage.

People

Marcelo Sandoval-Castañeda

University of California Berkeley

Gregory Shakhnarovich

TTIC

Talks

Avatar Aang: The Last Airbender - Hybrid Stylization A Contextual Approach to the Painterly Aesthetic

2:40pm - 3:00pm PDT Sunday, 19 July 2026 Room 515 A

Arts & Design

Production & Animation

Animation

Art

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionFlying Bark Productions introduces an NPR workflow for Avatar Aang: The Last Airbender (feature) that shifts final stylization to Compositing, integrating directly with background paintings. Using Local Position and Tangent Field Vectors, it generates and smears procedural strokes in 2D screen space, enabling painterly stylization, dynamic lighting, and temporal stability.

People

Chris Barischoff

Navneet Rao

Quentin Destais

Jerry Huynh

Paramount Animation

Guillem Ramisa De Soto

Avatar Aang: The Last Airbender - Strike Force A Hybrid In-House Production Model for a Modern 2D/3D Animated Feature Pipeline

Talks

9:40am - 10:00am PDT Sunday, 19 July 2026 Petree D

Production & Animation

Animation

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

DescriptionParamount Animation formed a multidisciplinary “Strike Force” during Avatar Aang: The Last Airbender (feature) to support a distributed, vendor‑based pipeline. The team paralleled work across global studios while building an in‑house pipeline for finaling, FX, layout, and compositing. This document details the group’s purpose, workflows, tools, and outcomes under tight constraints.

People

Karyn Buczek Monschein

Paramount Animation

Vijoy Gaddipati

Paramount Animation

Computer Animation Festival

Azimuth

12:30pm - 1:30pm PDT Thursday, 23 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionHadenna, a young warrior, travels across the galaxy in search of the ultimate cure to restore her brother, Theos, to his true body.

People

Director

Director

Director

Director

François-Clement Michez

Director

Director

Director

Technical Paper

B-repLer: Language-guided Editing of CAD Models

11:05am - 11:15am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionCurrent language-guided CAD editing struggles with dataset shortages and relies on construction history. We introduce B-repLer, a novel framework enabling text-based CAD edits in a learned latent space without requiring construction history. We also present BrepEDIT-240K, the first large-scale editing dataset, enabling accurate, complex CAD edits from high-level text commands.

People

Yilin Liu

Niladri Shekhar Dutt

Changjian Li

Niloy J. Mitra

Beaver World: Integrating Indigenous Wisdom and Ecological Simulation in a 3D Educational Game

Educator's Forum

4:25pm - 4:45pm PDT Wednesday, 22 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Digital Twins

Education

Games

Generative AI

Real-Time

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionBeaver World uses beaver-based simulation to teach watershed restoration, integrating Indigenous ecological knowledge with climate education.

People

Yuanyuan Xu

Chi Zhen

Obiajulu Nwosisi

Amir Rahsaz

Tanhab Sarker

Miles Thorogood

Patricia Lasserre

Aleksandra Dulic

Behind ReVerie: Sense: Designing Interactive Fulldome Experiences with 3D Generative AI and Robotic Interfaces

Talks

2:40pm - 3:00pm PDT Sunday, 19 July 2026 Room 408 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Games

Generative AI

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionReVerie: Sense is an interactive and co-creative fulldome installation that explores the use of 3D generative AI and a multisensory robotic sculpture for transmedia storytelling. In this talk, we present the creative R&D process, offering reflections on designing with generative AI for expanded storytelling with an immersive and somatic approach.

People

Pinyao Liu

Independent Artist

Spatial Storytelling

Behind the Scenes at The New York Times R&D: Spatial Storytelling

1:00pm - 1:45pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

New Technologies

Research & Education

Capture/Scanning

Digital Twins

Spatial Computing

Full Conference Supporter

Full Conference

Experience

Description"The New York Times has an R&D team?" In our industry dedicated R&D is rare. We make space for technologists and journalists to pilot new ways of reporting stories. Learn how we navigate journalistic constraints, pioneer spatial storytelling techniques, and bridge gaps between emerging technology and traditional journalism workflows.

People

Birds of a Feather

Berthouzoz Women in Research Lunch

12:30pm - 2:00pm PDT Wednesday, 22 July 2026 JW Marriott - Plaza 2-3

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Chapters

Computer Vision

Digital Twins

Display

Diversity, Equity and Inclusion

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

History

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Networking

Performance

Physical AI

Pioneers

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionThe Berthouzoz Women in Research Event is an annual networking event organized by WiGRAPH for researchers, faculty, and students. Floraine Berthouzoz started this event as an informal gathering.
After her passing in 2015, Floraine's mentees and colleagues built upon her efforts to create an event that aims to broaden the network of women researchers and provide a friendly and personal environment where graduate students can interact with senior researchers. We will be hosting a panel of women in graphics who will share with us some of their research experiences. The event is open to all researchers, regardless of gender.

People

ACM SIGGRAPH 365

Best of Eurographics 2026

2:15pm - 3:15pm PDT Monday, 20 July 2026 Room 404 AB

Research & Education

Animation

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionFollowing the success of last year’s edition, this session will present a curated selection of outstanding research contributions from the Eurographics 2026 conference. The session aims to provide SIGGRAPH attendees with insights into current trends, emerging directions, and key developments in Computer Graphics and related fields, with a particular focus on research originating from the European community and its global impact.

The session will open with a short introduction to Eurographics, followed by presentations of the selected works and awards, in particular:
- The Best Paper Award of Eurographics 2026
- The Selected Honourable Mentions of the Best Paper Award of Eurographics 2026
- The recipient of the Eurographics Young Researcher Award 2026

People

Better Bending: Analysis, Construction and Verification of Discrete Bending Models for Kirchhoff-Love Shells

Holger Theisel

Eurographics

Universität Magdeburg

Technical Paper

11:15am - 11:25am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWhile thin shells have been studied for decades, there is little consensus on how to discretize them. We systematically study bending models for Kirchhoff-Love shells. We develop new models and methods to address discovered simulation gaps, and make practical recommendations of when and how these models should be used.

People

Beyond Computational Design: Design Intelligence and the Future of Creative Systems

ACM SIGGRAPH 365

9:00am - 10:00am PDT Monday, 20 July 2026 Room 404 AB

Arts & Design

Ethics and Society

Generative AI

Full Conference Supporter

Full Conference

Experience

DescriptionComputational design reshaped interactive media, product design, and architecture over the past two decades. What comes next?

This SIGGRAPH 365 session puts that question to the ACM SIGGRAPH Design Affinity Group, tool-makers and educators who have shaped computational design practice and its platforms. In a sequence of short provocations, panelists will stake out what supersedes computational design: where AI, generative methods, and open frameworks are taking creative practice, and how future tools can support human agency and collaborative forms of design.

The talks will open a discussion on bridging domains: interaction and UX designers, visual and graphic designers, industrial and product designers, as well as architects, have been part of SIGGRAPH since its inception, but have remained at its edges. The Design Affinity Group exists to move them closer to the center. We want your take on what advocacy for design within SIGGRAPH should look like.

People

Joanna Berzowska

Associate Professor

Concordia University

Masa Inakage

Dreamer

The Media Studio Inc.

Joanna Berzowska

Associate Professor

Concordia University

Marcelo Coelho

Associate Professor

Design Intelligence Lab MIT Department of Architecture

Aisling Kelliher

Associate Professor of Cinematic Arts

Media Arts + Practice Division

Nicolas Henchoz

École Polytechnique Fédérale de Lausanne (EPFL)

EPFL+ECAL Lab

Makai Smith

Principal, Digiplasty

Digiplasty

Birds of a Feather

Beyond Eyeballing: The Need for Standardized Assessment in AI-Driven Rendering

3:00pm - 4:30pm PDT Sunday, 19 July 2026 Room 510

Gaming & Interactive

New Technologies

Artificial Intelligence/Machine Learning

Computer Vision

Generative AI

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionThe shift from native graphics rendering to AI-driven neural rendering (NVIDIA-DLSS, AMD-FSR, Intel-XeSS) has fundamentally disrupted how the video game industry measures visual fidelity. Traditional objective metrics no longer suffice, leaving developers, QA testers, and reviewers to rely on subjective "eyeballing". Following the enthusiastic response to our 2025 BoF, we return to continue the conversation. This session will explore the fragmentation of quality assessment in modern game development workflows, the severe economic costs of manual visual QA, and how the interactive entertainment industry can learn from established telecommunications standards (such as ITU and VQEG) to build automated, objective quality metrics.

People

Technical Paper

Beyond Positional Encoding: A 5D Spatio-Directional Hash Encoding

11:35am - 11:45am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionThis paper introduces two new compact neural encodings, the hash-sphere and hash-grid-sphere, which represent all-frequency signals using hierarchical geodesic grids. While we demonstrated their effectiveness in neural path guiding, radiance field reconstruction, and incident radiance caching, these versatile "drop-in" replacements offer significant potential for various applications across computer graphics.

People

Games Summit

Beyond the Dot: New Ways to Reduce Motion Sickness in Gaming

10:00am - 10:30am PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionMotion sickness remains a significant barrier to immersive games, affecting up to one-third of players. We present a player-centered mitigation approach developed within a kinetic first-person game, reframing motion comfort as accessibility and embedding inclusive design directly into gameplay systems, supported by empirical adoption and impact data.

People

Birds of a Feather

Beyond the Score: Interpreting Graphics Benchmark Results for Better System Decisions

10:30am - 11:30am PDT Thursday, 23 July 2026 Room 518

Research & Education

Hardware

Industry Insight

Performance

Full Conference Supporter

Full Conference

Experience

DescriptionGraphics benchmark scores are often used to compare systems, evaluate hardware, and guide purchasing decisions, but results are easier to quote than to interpret. Their meaning depends on the workload, system configuration, and bottlenecks behind the measurement. This talk explores how workload design, display resolution, system balance, driver behavior, and software optimization shape measured graphics performance, and how average scores can obscure behavior that affects real-world user experience. Attendees will learn how to ask better questions of benchmark data, recognize what results do and do not represent, and apply them more effectively when comparing systems and selecting the right configuration.

People

Brigit Valencia

Standard Performance Evaluation Corporation

Anthony Mansur

Standard Performance Evaluation Corporation

Intel

Rizu Jain

Standard Performance Evaluation Corporation

BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer

Computer Animation Festival

Beyond Words

12:30pm - 1:30pm PDT Wednesday, 22 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionIn a viking world, a girl’s mother goes to battle following her husband’s death.
But the emotions stemming from this distance haunt them and mysterious wolves appear..

People

Director

Director

Director

Director

Director

Director

Director

Director

Director

Director

Director

Technical Paper

9:10am - 9:20am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionBFS is a novel generation-based framework for layered image synthesis that produces foreground layers with realistic visual effects while harmonizing with a given background. Using a dual-branch diffusion model and two-stage training with unlayered data, it overcomes data scarcity and achieves superior quality and diversity compared to prior methods.

People

Talks

Blazing a New Trail of Curls

9:00am - 9:20am PDT Thursday, 23 July 2026 Room 515 A

New Technologies

Production & Animation

Animation

Dynamics

Geometry

Industry Insight

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionFor Disney/Pixar’s Toy Story 5 character Blaze, we developed a grooming structure for tightly coiled curls, enabling rapid artistic iteration. We deployed Fizt Strands, built on our Fizt cloth solver, offering superior hair collision and stability. These advancements enabled believable curl simulation, complimenting the character’s ethnicity and personality.

People

Jacob Brooks

David Eberle

Alan Browning

Blender Foundation - Community meetup

Birds of a Feather

4:00pm - 6:00pm PDT Monday, 20 July 2026 Room 518

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Digital Twins

Education

Ethics and Society

Games

Image Processing

Pipeline Tools and Work

Real-Time

Rendering

Scientific Visualization

Simulation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionBlender Foundation will present an overview of past year's Blender open source project results and the plans for next year. Everyone is welcome for feedback and share experiences.

People

Francesco Siddi

Blender Foundation

Computer Animation Festival

Blooky: The Book Who Wanted to be Read

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionJust as he’s about to be placed in the Classics section, a little book named Blooky is accidentally misplaced and ends up lost in the endless shelves of a grand library. From Business and Arts to Politics and even Horror, he explores every aisle, only to be rejected again and again. But when he finally finds a shelf that seems just right, he must decide whether to take his place or help a lonely child who, like him, was cast aside.

People

Pablo Diaz De Leon Hicks

Director, Writer, Animator

Blurring the Line Between Real and Digital Water in Avatar: Fire and Ash

Talks

4:05pm - 4:25pm PDT Tuesday, 21 July 2026 Room 403 B

Production & Animation

Research & Education

Animation

Art

Capture/Scanning

Digital Twins

Dynamics

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionAvatar: Fire and Ash required geometric consistency between photographed and simulated water in chaotic tank environments over long frame sequences, with characters interacting directly with the surface. We describe a feature-driven approach for recovering temporally coherent water motion to support stable parametric modeling and simulation coupling.

People

Lead FX Supervisor

Technical Paper

BodyReLux: Temporally Consistent Full-Body Video Relighting

2:00pm - 2:10pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Lighting

Full Conference Supporter

Full Conference

DescriptionBodyReLux is a video diffusion framework for relighting full-body human performances with photorealistic, temporally consistent results. Trained on video relighting pairs captured on large LED Sphere using digital bi-pack technology, it enables precise, dynamic lighting control and generalizes robustly to in-the-wild videos.

People

Technical Paper

Boundary-aware Neural Model Reduction for PDEs

9:00am - 9:10am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionNeural eigenanalysis enables reduced-order modeling across shape families but is limited to Neumann boundaries. We extend it to Dirichlet, Robin, and mixed conditions by treating boundary configurations as inputs, forming a unified shape–boundary space for consistent spectral analysis and simulation across varying geometries and boundary settings.

People

Li Liao

Pengfei Shen

Bounding Stratified Bernoulli Impulses for Ray Marching Gaussian Process Implicit Surfaces

Technical Paper

2:40pm - 2:50pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionIn this paper, we present an optimized algorithm for rendering Gaussian Process Implicit Surfaces (GPISes). By using stratified Bernoulli impulses, we precompute point-level bounds stored in a bound map. We also represent region-level bounds with a spatial data structure. Combining these bounds, we achieve significant improvements in rendering performance.

People

Mohamed bin Zayed University of Artificial Intelligence

Institute of Hangzhou Holographic Intelligent Technology

Jie Guo

BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing

Technical Paper

10:45am - 10:55am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionBoxCtrl introduces a 3D-aware visual prompting framework for precise image editing. Using RGB 3D bounding boxes to decouple geometry from appearance enables accurate translation, rotation, and scaling. A two-stage training of first SFT and then Reinforcement Learning achieves superior precision and photorealism in geometric editing across diverse real-world data.

People

Feifei Wang

Shiyuan Yang

Xiaoyu Li

Tencent

Jing Liao

Breathing Life into Illustrations - Building a look for Stylized Compositing

Talks

2:00pm - 2:20pm PDT Sunday, 19 July 2026 Room 515 A

Arts & Design

Production & Animation

Animation

Art

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionThe team at Sony Pictures Imageworks developed a scalable compositing workflow for GOAT to achieve a hand-painted aesthetic. Deconstructing illustrations into a "recipe" of plug-and-play modules helped balanced stylization with efficiency. New pipelines for asset-based FX curves and 2D-to-3D sketch translation addressed the show's unique look-of-picture needs.

People

Megan Deane

Rebecca J. Lin

BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation

Technical Paper

11:25am - 11:35am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionBrepForge is a generative framework for CAD B-rep modeling that factorizes synthesis into wireframe construction and boundary-conditioned surface generation. This two-stage design improves topological validity and geometric precision, enabling the creation of complex and realistic CAD models.

People

Jing Li

Yihang Fu

Falai Chen

Bridging Artistic Expression and Game Design through Cross-Cultural Collaboration: An Educational Framework from a Seven-Year Japan–U.S. Program

Educator's Forum

4:25pm - 4:45pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

Research & Education

Animation

Art

Education

Games

Scientific Visualization

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper reports an eight-year Japan–U.S. collaborative game-making program between an art university and a game program. We present a transferable educational framework that bridges artistic expression and system-oriented game design. Qualitative observation identifies three strategies: role-fluid teams, intent-driven interaction design goals, and the pedagogical use of cross-cultural differences.

People

Nahomi Maki

Mitsuko Okamoto

Takashi Kiriyama

Peter Brinson

Andreas Kratky

Bring Your Bunny (or Something) 05: Fabrication Meet-up

Birds of a Feather

4:30pm - 6:30pm PDT Monday, 20 July 2026 Room 512

Arts & Design

Research & Education

Art

Fabrication

Geometry

Full Conference Supporter

Full Conference

Experience

DescriptionThis event will provide an opportunity for those working on fabrication to meet others and share their experiences. We encourage them to bring physical objects (fabrication results) to make it a fun event. We plan to invite people working on fabrication widely using our own connections, but also welcome anybody interested in this topic. This will be the 5th “Bring Your Bunny (or Something)” BoF event with previous events taking place at SIGGRAPH in 2023, 2024, and 2025, and SIGGRAPH Asia in 2024.

People

Quentin Becker

Anran Qi

Takeo Igarashi

Free University of Bozen-Bolzano

Koya Narumi

Keio University

Michael Haller

Technical Paper

Bringing Diversity from Diffusion Models to Semantic-Guided Face Asset Generation

2:30pm - 2:40pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionThis paper introduces a framework for generating high-quality, semantically controllable facial assets. By leveraging a diffusion model's diversity, we develop a face asset synthesis pipeline to produce paired albedo and geometry data with semantic labels. These pairs are then used to train a disentangled GAN, enabling precise latent editing of the generated assets while preserving identity.

People

Yunxuan Cai

University of Southern California Institute for Creative Technologies

Sitao Xiang

University of Southern California Institute for Creative Technologies

Zongjian Li

University of Southern California Institute for Creative Technologies

Haiwei Chen

University of Southern California Institute for Creative Technologies

Yajie Zhao

University of Southern California Institute for Creative Technologies

Yunxuan Cai

Bringing The Mandalorian and Grogu to Life: Virtual Production, Creatures, and VFX Innovations

Production Session

4:15pm - 5:15pm PDT Wednesday, 22 July 2026 Hall K

Production & Animation

Animation

Lighting

Modeling

Performance

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionIndustrial Light & Magic invites you behind the scenes of The Mandalorian and Grogu for an in-depth exploration of the visual effects that brought the latest Star Wars feature to life. In this panel, the filmmakers and artists will unpack how groundbreaking real-time technology, virtual production workflows, and time-tested VFX techniques came together to create immersive worlds, unforgettable characters, and epic action on the big screen. From on-set innovation to final pixels, join the ILM team as they share creative insights, technical breakthroughs, and lessons learned while pushing the boundaries of modern visual storytelling.

People

John Knoll

Executive Creative Director/Sr. VFX Supervisor

Industrial Light & Magic

Hal Hickel

Animation Supervisor

Industrial Light & Magic

Rebecca Forth

Senior Look Development Lighting Technical Director

Industrial Light & Magic

Technical Paper

Broadband Hyperspectral 3D Imaging using Dispersed Structured Light

2:30pm - 2:40pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

DescriptionWe present a broadband hyperspectral 3D (BH3D) imaging system spanning visible to SWIR (450–1500 nm). Using a single-spectrograph stereo setup, our method jointly reconstructs accurate 3D geometry and material properties, enabling robust analysis of real-world scenes beyond the visible spectrum.

People

Kyros Kutulakos

BruSHŪ: Cross-Modal Translation of Implicit Micro-Actions in Chinese Calligraphy

Seung-Hwan Baek

POSTECH

Art Paper

11:45am - 12:05pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Digital Twins

Display

Dynamics

Education

Ethics and Society

Games

Geometry

Hardware

Lighting

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionBruSHŪ is a sensor-embedded calligraphy brush that translates fleeting micro-actions, contact boundaries, turns, and hesitations into sparse sound events and an evolving ink-like visual field. Rather than scoring or reconstructing strokes, it makes tacit embodied decisions perceptible and discussable in real-time, advancing non-normative, cross-modal feedback for reflective creative practice.

People

Tiancheng LIU

Hong Kong University of Science and Technology (Guangzhou)

Shumeng Zhang

Hong Kong University of Science and Technology (Guangzhou)

Nicolò Merendino

The Hong Kong University of Science and Technology (Guangzhou)

Talks

Brushing Up on Illumination: Temporal Coherence in Painterly Compositing in Disney and Pixar’s Hoppers

3:00pm - 3:20pm PDT Sunday, 19 July 2026 Room 515 A

Arts & Design

Production & Animation

Animation

Art

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionFor Pixar’s "Hoppers", the artistic vision called for a distinctive painterly aesthetic that would give the film a handcrafted, illustrative quality while maintaining our sophisticated lighting and color work. This talk presents the Paintbrush Pipeline, a flexible asset and compositing approach developed to balance artistic control with technical requirements.

People

Greg Finch

Jon Reisch

FX Supervisor

Dan Enstrom

Chia-chi Hu

Building and Transitioning the Rainbow Affinity Group

ACM SIGGRAPH 365

2:15pm - 3:15pm PDT Wednesday, 22 July 2026 Room 404 AB

Research & Education

Diversity, Equity and Inclusion

Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionThe ACM SIGGRAPH Rainbow Affinity Group was formally established in June 2025 to support LGBTQ+ individuals in computer graphics and interactive techniques. Participants throughout the years of the Rainbow Meetup Birds of a Feather articulated strong interest in mentorship, networking, and inclusive programming. This session continues that discussion and provides a framework for action.
This session presents the Rainbow Affinity Group as an active organizational design and transition effort. We reflect on early community input, examine the gap between ideation and execution, and introduce a structured model for forming a working committee to support future programming and leadership development.
Through a facilitated discussion, attendees will be invited to help define priorities and identify pathways for participation. The session will initiate the formation of a new contributor cohort aligned with defined roles in programming, mentorship, communications, and industry engagement. This cohort will form the foundation for the group's next phase and future leadership, in alignment with ACM SIGGRAPH governance practices.
This special session features invited speaker Kevin McKeon, a director at Netflix overseeing live-action family and all-audience original feature films. Prior to Netflix, Kevin served as Senior Vice President of Production at Mattel Films, where he shepherded projects including the 2023 Best Picture Oscar nominee Barbie, Masters of the Universe, the upcoming feature, A24's Barney, and the J.J. Abrams-produced Hot Wheels. In a moderated discussion, Kevin will share his experiences in the industry, with an inspirational focus on how identity can be an asset. Light food and drinks will be provided.

People

AJ Christensen

University of California Santa Cruz

Daniel Pillis

Emerson College

Jeffrey D. Weekley

University of California Santa Cruz

Birds of a Feather

Building the Future of Web Graphics with WebGL and WebGPU

9:00am - 10:00am PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

Gaming & Interactive

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Games

Graphics Systems Architecture

Performance

Real-Time

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionJoin the Khronos Group, browser developers, and the web graphics community for an interactive look at the latest advances in WebGL and WebGPU. Explore new capabilities for real time rendering, compute, AI, tooling, and cross platform deployment, along with the evolving ecosystem across browsers, frameworks, game engines, and immersive web experiences. Hear from developers building the future of 3D on the web, ask questions, share feedback, and help shape what comes next for web graphics.

People

Stage Session

Building the Interactive Future: Inside Tripo's Full-Stack 3D Generation Ecosystem

4:00pm - 4:30pm PDT Tuesday, 21 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Animation

Art

Artificial Intelligence/Machine Learning

Games

Generative AI

Modeling

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionWhile text and image AI have seamlessly integrated into daily workflows, 3D generation remains uniquely challenging. In this session, the Tripo AI research team examines why 3D demands specialized architectures, and demonstrates the full-stack generative ecosystem built to address it.

Moving beyond the generation of unstructured meshes and baked textures, the team will detail Tripo's latest foundational models, highlighting H-series for high-fidelity geometry and texturing, alongside P-series for extremely fast, production-grade mesh topology. Through live demonstrations, attendees will see how these architectures output clean assets complete with semantic segmentation and automatic rigging, i.e., capabilities that are directly integrated into pipelines for gaming, 3D printing, and interactive media.

The session concludes by shifting focus from object generation to environment simulation. Leveraging massive-scale architectures and multimodal integration, the Tripo team will preview their ongoing R&D in Generative World Models, demonstrating how the field is advancing toward dynamic environments, agentic systems, and world modeling

People

Tripo AI Research Team

Tripo AI

Course

Building with Meta Wearable Device Access Toolkit

2:00pm - 5:15pm PDT Monday, 20 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Augmented Reality

Education

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionCreate at the forefront of spatial computing with Meta’s Wearable Device Access Toolkit. This immersive, 3-hour course offers hands-on access to our AI Glasses hardware and sensor data, empowering attendees to build privacy-aware, innovative AI Glasses applications. Participants will advance wearable technology setting new standards for responsible, visionary digital experiences.

People

Yağız Mungan

Reality Labs, Meta

Purdue University

Technical Paper

Buoyancy-driven Phase Separation in the Material Point Method

10:55am - 11:05am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionThe Material Point Method struggles with separating materials due to a shared background grid that couples velocities. We introduce a hybrid approach using separate velocity grids and a unified pressure model, enabling buoyancy-driven phase separation for immiscible fluids.

People

Mehrnaz Ayazi

University of California Riverside

Craig Schroeder

University of California Riverside

Tamar Shinar

University of California Riverside

Technical Paper

C^0 Generalized Coons Volumes over Arbitrary Polyhedra

11:35am - 11:45am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionIn this paper, we generalize the Coons volume from hexahedral topology to arbitrary polyhedral topologies via generalized barycentric coordinates. We prove that the proposed generalized Coons volume possesses several desirable geometric properties and demonstrate its applications in computer graphics.

People

Kaikai Qin

Zeqi Ge

Budapest University of Technology and Economics

Péter Salvi

Chenhao Ying

CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation

Technical Paper

2:30pm - 2:40pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionCAdam resolves the mismatch between reconstruction-native densification and stochastic generative guidance in optimization-based 3DGS. By reinterpreting densification as statistical signal verification via momentum and context-adaptive selection, it reduces Gaussian primitives by 85%–97% across diverse backbones while preserving comparable perceptual quality, making generative 3DGS far more compact and practical.

People

Technical Paper

CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting

11:05am - 11:15am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionCAGS is a novel color-adaptive system for 3D Gaussian Splatting that enables high-quality, immersive volumetric video streaming. By utilizing vector quantization and reference images for color restoration, CAGS overcomes bandwidth limitations, delivering significantly faster speeds and superior visual quality compared to existing solutions under fluctuating networks.

People

Daheng Yin

Yili Jin

McGill University

Jianxin Shi

Nankai University

Isaac Ding

Miao Zhang

Fangxin Wang

Jiangchuan Liu

CameraSquad: Achieving Content Consistency in Parallel Multi-Trajectory Camera-Controlled Video Generation

Fang Dong

Southeast University

Technical Paper

9:50am - 10:00am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

DescriptionCameraSquad is a multi-trajectory camera control framework that supports both single-trajectory and parallel multi-trajectory video generation. By decoupling content and camera control mechanisms and using a dual-mode cross-view attention mechanism, it ensures viewpoint consistency and camera control precision in multi-trajectory mode.

People

Zhufeng Xu

Institute of Computing Technology, Chinese Academy of Sciences

Institute of Computing Technology, Chinese Academy of Sciences

Xuan Gao

School of Computer Science and Informatics, Cardiff University

Bailin Deng

Yikang Ding

Xiaoqiang Liu

Haoxian Zhang

Pengfei Wan

Institute of Computing Technology, Chinese Academy of Sciences

Lin Gao

Can AI Judge Its Own Work? Self‑Assessment and Trust in Creative AI Pipelines

Birds of a Feather

9:30am - 10:30am PDT Monday, 20 July 2026 Room 510

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Ethics and Society

Games

Generative AI

Industry Insight

Pipeline Tools and Work

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionGenerative and agentic AI increasingly grades its own output. VLM and LLM judges decide when a result is good enough, confidence scores gate quality, and autonomous tools self‑terminate. But when can we trust an AI's assessment of its own work? This facilitated discussion gathers researchers and practitioners across graphics, vision, HCI, and production to compare notes on AI self‑assessment and calibration. We will discuss where self‑scores break down, how overconfidence hides in iterative loops, and which external‑validation strategies work (second‑model judges, geometric checks, human review). Bring your own failure cases. Researchers, engineers, and students welcome.

People

Tyler Varacchi

Drexel University

Birds of a Feather

CANCELED: AI-Driven Data Pipelines for Digital Twins and Simulation

11:30am - 12:30pm PDT Sunday, 19 July 2026 Room 513

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Digital Twins

Generative AI

Industry Insight

Physical AI

Pipeline Tools and Work

Real-Time

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionAI is transforming how digital twins and simulations are built, fed, and maintained but connecting intelligent pipelines across fragmented tools and formats remains a hard, unsolved problem. This facilitated discussion brings together practitioners from film, games, architecture, and engineering to share real-world experience building AI-powered data pipelines: automated ingestion, anomaly detection, model-driven transformation, and live feedback loops between simulation and physical systems. What is working in production? Where does AI add genuine value versus hype? Come exchange honest lessons and push the conversation forward on what AI-driven pipeline infrastructure actually looks like at scale.

People

Viv Devadas

MottMacDonald

Autodesk Alumni

Birds of a Feather

CANCELED: Everyone Is an Obscure Artist: Living Lineages in Computational Creativity

5:00pm - 6:00pm PDT Wednesday, 22 July 2026 Room 512

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Chapters

Computer Vision

Digital Twins

Display

Diversity, Equity and Inclusion

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

History

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Networking

Performance

Physical AI

Pioneers

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionFame is an edge case. Obscurity is the normal condition of creative work.

Important creative technology often appears first as demos, tools, performances, installations, prototypes, virtual worlds, and interactive systems — not papers. Even when formally presented or archived, these works can disappear from the field’s working memory because research culture transmits papers better than living artifacts.

This BOF invites artists, researchers, tool-builders, educators, and independent creators to discuss how experimental work becomes legible, transmissible, and buildable across computer graphics, AI, XR, animation, games, and computational performance.

The goal is continuity: a living support network for work carried forward.

People

Yosun Chang

AI3D.Foundation

AIMagical

Technical Paper

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

9:40am - 9:50am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionCanvas-to-Image is a unified framework enhancing diffusion models' compositional and multimodal control through a single canvas interface. By encoding subject references, bounding boxes, and poses into one composite canvas, it enables integrated visual-spatial reasoning. This approach streamlines heterogeneous control signals, allowing models to generate high-fidelity images with precise structural alignment.

People

Yusuf Dalva

Virginia Tech University

University of California Merced

Virginia Tech University

Kuan-Chieh Jackson Wang

Snap

Computer Animation Festival

Captives

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionThis film denounces intensive livestock farming by evoking the imprisonment, sadness and resilience of a cow separated from her calf, in a heavy and poignant atmosphere.

People

Director

Director

Director

Director

Director

Director

Director

Technical Paper

CaRaFe: Camera-Radar Radiance Fields for Scene Reconstruction

11:05am - 11:15am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionCaRaFe is the first method to jointly reconstruct 3D scenes from both camera and radar data using a multi-modal shared neural geometry representation. It can reconstruct large-scale urban environments from a single drive-through and synthesize measurements from both sensors at novel viewpoints, leveraging their complementary strengths to improve geometric fidelity.

People

Technical University of Munich

Technical Paper

CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling

9:10am - 9:20am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionCasLayout is a cascaded diffusion framework that decomposes 3D indoor scene generation into four interpretable stages. This design reduces data requirements while enabling flexible, controllable synthesis and seamless integration with LLMs and VLMs for zero-shot tasks.

People

Yingrui Wu

Institute of Automation, Chinese Academy of Sciences

School of Artificial Intelligence, University of Chinese Academy of Sciences

You-Kang Kong

State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences

Mingyang Zhao

Weize Quan

Institute of Automation, Chinese Academy of Sciences

Dongmin Yan

Institute of Automation, Chinese Academy of Sciences

ACM SIGGRAPH 365

Chapters Party

9:00pm - 11:59pm PDT Monday, 20 July 2026 Exchange LA, 618 S. Spring Street

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionCelebrate the start of SIGGRAPH with an evening you won't want to miss! Join the ACM SIGGRAPH Chapters Committee from 9 pm to 1 am on Monday, July 20 at Exchange LA for a night of fun with the world’s greatest pixel wranglers. All registration levels are welcome, and your conference badge is your entry ticket! You must be of legal drinking age to attend and provide a valid photo ID in order to enter the club. The venue is a 10 minute car ride away from the Los Angeles Convention Center at 618 S Spring Street, Los Angeles, CA. Ask for more information at the ACM SIGGRAPH Village!

People

Chapters: East Coast Meetup

ACM SIGGRAPH 365

4:45pm - 5:45pm PDT Monday, 20 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionIn conjunction with the Professional and Student Chapters Committee (PSCC), leaders from chapters on the East Coast of North America welcome you to join a social hour to connect with other students and professionals. This session will give information on chapters in the area, the activities they host, and ways to get involved.

More information about the PSCC, chapters near you and how to get involved can be found at https://siggraph.org/chapters.

People

Philadelphia ACM SIGGRAPH Professional Chapter

Anjelikal Rogers

Natasha Warshawsky

Chapters: West Coast Meetup

ACM SIGGRAPH 365

1:00pm - 2:00pm PDT Wednesday, 22 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionIn conjunction with the Professional and Student Chapters Committee (PSCC), leaders from chapters on the West Coast of North America welcome you to join a social hour to connect with other students and professionals. This session will give information on chapters in the area, the activities they host, and ways to get involved.

More information about the PSCC, chapters near you and how to get involved can be found at https://siggraph.org/chapters.

People

Los Angeles Professional ACM SIGGRAPH Chapter

Joan Collins

Sunil Rampersad

Chasing De’Snake! - Developing the Worlds and Characters of Disney’s “Zootopia 2”

Production Session

9:30am - 10:30am PDT Tuesday, 21 July 2026 Hall K

Production & Animation

Animation

Art

Geometry

Image Processing

Industry Insight

Lighting

Modeling

Pipeline Tools and Work

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWhen building upon a beloved franchise like Zootopia, the artists of Walt Disney Animation Studios had to consider every detail that makes the world unique and its characters memorable. By combining the famous bunny and fox duo with a herd of new animated animals and environments, artists developed new rules and techniques to expand the world in genuine and exciting ways.

In this session, the “Zootopia 2” leadership team will take you on a wild journey through the film’s worldbuilding. They will explore what it took to visualize marshes, mountains, deserts, and tundra, and discuss the development of new characters like Gary De’Snake and the Lynxley family. They will also share new workflows and tools throughout the discussion that allowed for collaboration across multiple departments, and enabled the crew to tackle an adventurous and expansive body of work.

People

Jack Fulmer

Head of Environments

Adam Green

Animation Supervisor

Kira Lehtomaki

Head of Animation

David Hutchins

Head of Effects Animation

Tyler Kupferer

Director of Cinematography Layout

Daniel Rice

Director of Cinematography Lighting

Cheap and Cheerful: Low-Fidelity Prototyping for Spatial Stories

Spatial Storytelling

2:00pm - 2:35pm PDT Wednesday, 22 July 2026 Concourse Hall

Gaming & Interactive

Art

Games

Real-Time

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis talk explores "cheap and cheerful" prototyping in immersive storytelling through the evolution of THE FOOTAGE, a VR narrative horror game. It traces how low-fidelity, no-code, and provisional methods surfaced crucial spatial insights, guided design decisions, enabled play-testing, and helped secure funding before full-scale production.

People

Ethan Shaftel

easyAction

Talks

Chem2Vid: Translating Chemical Equations into Videos for Chemistry Education via Chemically Constrained Diffusion

10:00am - 10:20am PDT Sunday, 19 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Digital Twins

Education

Fabrication

Games

Generative AI

Geometry

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionChem2Vid introduces a multimodal framework translating chemical equations into dynamic, chemically faithful videos for education. It integrates LLMs and chemical simulators with diffusion models to generate stoichiometry-constrained reaction visualizations and synchronized property curves, creating a low-cost virtual laboratory to enhance chemistry understanding.

People

Baotong Qian

Beijing Technology and Business University (BTBU)

Qian Zhang

Beijing Technology and Business University (BTBU)

Xiaoming Chen

Beijing Technology and Business University (BTBU)

Yongquan Hu

National University of Singapore (NUS)

Industry Session

Cloud Arena: Bringing Real-Time Ray-Traced Virtual Production to the Global Cloud

3:00pm - 3:50pm PDT Tuesday, 21 July 2026 Room 511C

Gaming & Interactive

New Technologies

Games

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionAs Virtual Production continues to transform filmmaking, the demand for scalable, accessible infrastructure is growing beyond the walls of traditional studios. In this session, Eric Pinkel of CenterGrid will present Cloud Arena, a collaborative research initiative exploring how real-time ray-traced Virtual Production workflows can be deployed across globally distributed cloud infrastructure.

Using CenterGrid VFX Datacenter and Chaos Arena, the team successfully validated cloud-hosted rendering, cloud-hosted Arena services, and international operator workflows spanning North America and Europe. The presentation will walk through the project's milestone-based development process, system architecture, technical challenges, and key findings, including why synchronization and deterministic frame delivery have emerged as the next major frontier for cloud-native Virtual Production.

Attendees will gain insight into how cloud-based GPU workstations, remote rendering, and globally connected creative teams can expand access to Virtual Production technologies while enabling new workflows for studios, educators, and content creators worldwide.

People

Eric Pinkel

CenterGrid

Technical Paper

Co-Optimization of Structure and Manufacturable Semi-Continuous Layers for Laminated Composites

10:45am - 10:55am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionA field-based computational framework for designing fabric-reinforced composites with optimized topology and manufacturable semi-continuous layers, producing laminates up to 43.8% stiffer than conventional planar-ply designs.

People

Tao Liu

Aoran Lyu

Yongxue Chen

Yu Jiang

Michael James Petty

Coding Wagara: Fostering Motivation through Generating Japanese Patterns using SF Symbols

Charlie C.L. Wang

University of Manchester

Educator's Forum

4:05pm - 4:25pm PDT Wednesday, 22 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Digital Twins

Education

Games

Generative AI

Real-Time

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionBridging visual and syntax-based programming, this Art-Thinking curriculum fosters intrinsic motivation. By combining Apple’s SF Symbols to procedurally generate original Japanese patterns (Wagara), students master abstract concepts like coordinates and loops. This culturally responsive approach transforms syntax anxiety into "productive struggle," yielding tangible, creative outcomes.

People

Shinya Nishide

Senri International School of Kwansei Gakuin

Technical Paper

CoherentRaster: Efficient 3D Gaussian Splatting for Light Field Displays

11:45am - 11:55am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe propose CoherentRaster, an efficient 3D Gaussian Splatting-based light field rendering framework for glasses-free 3D displays. CoherentRaster introduces Cross-view Coherent Attribute Reuse to eliminate redundant computations across neighboring viewpoints and View-coherent Remapping to restore warp-level memory efficiency degraded by interlaced subpixel layouts, enabling real-time, high-quality synthesis.

People

Gyujin Sim

Pohang University of Science and Technology

Seungjoo Shin

Pohang University of Science and Technology

Hosung Jeon

Electronics and Telecommunications Research Institute (ETRI)

Gwangsoon Lee

Electronics and Telecommunications Research Institute (ETRI)

Hyon-Gon Choo

Electronics and Telecommunications Research Institute (ETRI)

Sunghyun Cho

Pohang University of Science and Technology

Educator's Forum

CollabXR: an open-source platform for immersive spatial communication of learning materials

11:45am - 12:05pm PDT Wednesday, 22 July 2026 Room 501 ABC

Gaming & Interactive

New Technologies

Research & Education

Augmented Reality

Digital Twins

Education

Games

Image Processing

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionCollabXR: a collaborative, multi-user XR platform that enables instruction, training and research through visualization and interaction with immersive three-dimensional materials. Originally designed for sharing astrophysics visualizations of supernova remnants in an 'XR classroom,' the platform has expanded to incorporate other 3D data from STEM, arts, humanities and cultural heritage.

People

Birds of a Feather

3:00pm - 4:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionColor Interop Forum

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Emily Ruf

Academy Software Foundation

Technical Paper

Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation

9:20am - 9:30am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionColorful-Noise is a training-free image generation conditioning method that leverages FFT noise frequency manipulation. We show that low frequencies dominate output appearance and can encode structure from scribbles, color maps, or reference images — enabling anyone to condition image generation with zero overhead, no training, and no significant artistic skill.

People

Talks

Coloring Outside the Pipeline: Stylized Pastel Techniques in Disney and Pixar's Toy Story 5

2:20pm - 2:40pm PDT Sunday, 19 July 2026 Room 515 A

Arts & Design

Production & Animation

Animation

Art

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionCreating Toy Story 5's hand-drawn "Playtime" sequences ventured outside Pixar's traditional pipeline via collaborative non-linear workflows spanning effects, shading, and compositing. The team developed pre-lit geometric pastel assets, stylized character treatments, and layered compositing approaches that transformed CG animation into ethereal pastel worlds visualizing childhood imagination.

People

Nate Skeen

Peter Demarest

Patrick Yu Wang

Ravindra Dwivedi

Dave Quirus

Max Gilbert

Laura Grieve

Alexander Alvarado

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

Technical Paper

9:50am - 10:00am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionWe study an important factor in diffusion generative models: combinatorial complexity. Existing training schemes insufficiently sample the joint space of dimensions and attributes, leading to weaker test time performance. We address this with ComboStoc, a simple stochastic process that better exploits underlying combinatorial structure.

People

Rui Xu

Jiepeng Wang

Hao Pan

Xin Tong

Complex-Valued Holographic Radiance Fields

Technical Paper

11:25am - 11:35am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionComplex-valued holographic radiance fields optimize holographic 3D scenes without relying on intensity-based intermediaries. Leveraging multi-view images, our method uses complex-valued Gaussian primitives encoding amplitude and phase aligned with scene geometry. This eliminates expensive single-view hologram recalculation, accelerating speed by 30×–10,000× while matching state-of-the-art quality, bridging wave optics and 3D scene geometry.

People

Yicheng Zhan

University College London

University College London

Yicheng Zhan

University College London (UCL), NA

Technical Paper

Component Modes Synthesis Method with Multiple Partitions for Large-scale Eigenvalue Problem

9:30am - 9:40am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionTo solve ultra-large-scale modal analysis problems, we extend Component Mode Synthesis (CMS) methods to use multiple partitions to generate more efficient local eigenbasis functions and reduce the computational cost of the low-frequency interface modes. We obtained the lowest 1500 eigenmodes of a model (30M DoFs) in 88 minutes.

People

Chongyao Zhao

Junzhou Yin

Independent Researcher

Hujun Bao

Jin Huang

Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes

Technical Paper

9:30am - 9:40am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionWe present a method for generating realistic multi-person interaction scenes from text. By modeling human pose and appearance together and composing scenes step by step, our approach produces images that better capture complex interactions, with improved accuracy and greater diversity compared to existing text-to-image models.

People

Technical Paper

Computational Design - Interactive Discussion

11:55am - 12:25pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Computational Design of Coordinate-Motion Assemblies

11:35am - 11:45am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a computational approach for designing contact-based coordinate-motion assemblies that meet user-specified target appearance and motion. One key enabler of our approach is that we established a theoretical connection between contact geometry within an assembly and unique coordinate motion of the assembly's parts.

People

Yukun Lu

Ke Chen

Peng Song

Computational Design of Terrestrial Robots with Anisotropic Friction

Technical Paper

11:45am - 11:55am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionThe interplay of morphology, control, and anisotropic friction makes optimal design for terrestrial locomotion challenging. We present a computational pipeline that co-designs friction and controllers across diverse robot morphologies, showing anisotropic friction is critical and achieving statistically superior performance over state-of-the-art methods.

People

Hang Hu

Kangbo Lyu

Computational Photography - Interactive Discussion

Technical Paper

3:00pm - 3:30pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

Art Paper

Computational Visual Semiotics: The “L” Programming Language by Frieder Nake

4:25pm - 4:45pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Display

Education

Fabrication

Generative AI

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Robotics

Full Conference Supporter

Full Conference

Experience

DescriptionThis study investigates Frider Nake's 1970 programming language "L" to explore the intersection of code and art. By examining how "L" translates programming languages into imaginative and intellectual explorations, we gain insights into the cultural dimensions of code and its potential as a medium for artistic production. This analysis deepens our understanding of how programming languages historically engaged with images, graphics and visual semiotics.

People

Andres Burbano

Universitat Oberta de Catalunya, UOC

Birds of a Feather

Computer Graphics & Animation Research Projects

1:00pm - 2:00pm PDT Tuesday, 21 July 2026 Room 510

Research & Education

Computer Vision

Education

Games

Full Conference Supporter

Full Conference

Experience

DescriptionNow in its fifth year, the Computer Graphics & Animation Research Projects program develops research initiatives in computer graphics and animation, then invites undergraduate students, in all disciplines, worldwide, to join our research project teams. We also invite faculty to join as project advisors. So come, hear about our projects, and share your experiences in research at the undergraduate level.

People

William Joel

Computer Graphics & Animation Research Projects

Birds of a Feather

Computer Graphics History Institute

2:00pm - 3:00pm PDT Monday, 20 July 2026 Room 512

New Technologies

Research & Education

Augmented Reality

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThe Computer Graphics History Institute (CGHI) is building a knowledgebase of computer graphics history. It has a twofold mission: a repository about the history of computer graphics, for education and reference, and technology bases for research into several areas, including HCI.

As a repository, the goal is to provide a starting point to learn about the history of computer graphics.

The knowledgebase is an RDF graph database. Research areas include history as KM, KM with XR, and interfaces based on cognitive science, where the primary interaction is an API to the human cognitive system.

There will be demos.

People

Julian Gomez

Comput er Graphics History Institute

Polished Pixels®

Birds of a Feather

Computer Graphics History: SIGGRAPH Stories and more…

1:00pm - 2:00pm PDT Tuesday, 21 July 2026 Room 512

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Generative AI

Graphics Systems Architecture

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionLove SIGGRAPH’s history? Curious about the people, projects, and milestones that shaped modern computer graphics? Join the ACM SIGGRAPH History Committee Birds of a Feather for a fun, informal gathering where attendees swap stories and share memories about SIGGRAPH, past and present. Whether you have a favorite conference moment, a behind-the-scenes anecdote, or a burning question about the early days of the field, this is the place to hear it and tell it. Come meet fellow history enthusiasts, learn what the committee has been working on and pitch ideas for new projects to help preserve SIGGRAPH's history.

People

Niall Williams

Barnard College

Chair

Constant Mean Curvature Surfaces from Discrete Harmonic Maps

Technical Paper

9:00am - 9:10am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe present a simple discretization of constant mean curvature surfaces based on the classical observation that their Gauss maps are harmonic. Our construction is elementary---requiring only discrete Dirichlet energy minimization and a Poisson solve---yet it exactly mirrors this aspect of the smooth theory.

People

Yousuf Soliman

Side Effects Software Inc

Peter Schröder

University of Bonn

California Institute of Technology

Ulrich Pinkall

Technical University of Berlin

Technical Paper

Continuity-Enhancing Degree Elevation and Splits

2:30pm - 2:40pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present two novel methods for automatically enhancing the continuity of piecewise-polynomial curves with negligible computational overhead. They provide the first practical interface for modeling curves with curvature (or higher) continuity using the familiar Bezier handles of piecewise cubic curves, the most popular curve modeling interface that previously offered no mechanism to achieve curvature continuity. Our solutions can also be used for defining new interpolating curve formulations with desirable properties. Furthermore, they can be used with higher-dimensional curves or surfaces, which we demonstrate by fixing the curvature discontinuities of the famous Utah Teapot model.

People

Cem Yuksel

Continuous Control of Editing Models via Adaptive-Origin Guidance

Technical Paper

11:05am - 11:15am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionDiffusion editing models lack smooth control over edit intensity, and scaling standard Classifier-Free Guidance fails to provide it. We introduce Adaptive-Origin Guidance (AdaOr), which dynamically adjusts the guidance origin using an identity-conditioned prediction. This enables continuous, fine-grained control over both image and video models at inference time without specialized datasets.

People

Technical Paper

Controllable Texture Tiling via Diffusion Transformers with Transformed Rotary Embeddings

10:45am - 10:55am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a novel Diffusion Transformer framework for high-fidelity, controllable texture tiling. By leveraging Coordinate-Transformed Rotary Embeddings, our method enables precise manipulation of texture frequency, scale, and orientation. It seamlessly integrates reference patterns into images while perfectly preserving the original scene's lighting and geometry.

People

Junrong Huang

Zhiyuan Zhang

Rui Tang

Manycore Tech Inc.

Jing Liao

Controlling the Frame: AI VFX, Generative Video, and the Future of Compositing

Birds of a Feather

2:00pm - 3:00pm PDT Monday, 20 July 2026 Room 513

Arts & Design

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Capture/Scanning

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionAI is rapidly reshaping VFX workflows, enabling tasks like relighting, background transformation, and look development to happen after capture. But as these systems become more capable, a central question emerges: how much control do artists actually retain?

This BOF explores the rise of controllable AI VFX and hybrid compositing workflows, where traditional techniques intersect with learned systems.

Drawing on emerging production practices, we invite artists, technologists, and researchers to discuss where these approaches succeed, where they break down, and how workflows are evolving across lighting, consistency, and creative intent.

People

Immersive Pavilion

Cosmos Unseen: Black Holes

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionFrom the award-winning storytellers at Atlantic Studios, Cosmos Unseen: Black Holes is a first-of-its-kind immersive experience that demystifies complex spacetime phenomena. Crafted for the launch of the Google x Samsung AndroidXR headset, Cosmos Unseen is a breakthrough in scientific storytelling, letting users get hands-on with the mysteries of our universe.

People

Birds of a Feather

Countering Racial Bias in Computer Graphics Research: Five Years Later

6:00pm - 7:00pm PDT Monday, 20 July 2026 JW Marriott - Plaza 1

Production & Animation

Research & Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionThis BOF is for attendees interested in discussing racial bias and related issues embedded in computer graphics research. It is a follow-on to similarly titled BOFs at SIGGRAPH 2021, 2022, 2024, and 2025. We will celebrate progress over the last five years, discuss setbacks, and brainstorm paths forward. This will be a friendly, collaborative space for mutual, authentic engagement across difference. Attendees can be at any stage, including learning about, taking steps toward, or enacting change in computer graphics research.

People

Crafting Feathers for the Bird Kingdom in Hoppers

Talks

10:00am - 10:20am PDT Thursday, 23 July 2026 Room 515 A

New Technologies

Production & Animation

Animation

Dynamics

Geometry

Industry Insight

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present the feather system for Disney/Pixar's "Hoppers," covering multiple bird species. We detail customizing Houdini's hair grooming pipeline, integrating groomed feathers into Presto character rigs, developing a flexible shading framework supporting patterns and two-sided coloration, and creating procedural and simulated flutter effects for natural animation and wind response.

People

Kiki Poh

Kris Campbell

Alan Browning

Michael Jefferies

Crafty Apes: Rendering at Scale with V-Ray

Industry Session

1:00pm - 1:50pm PDT Tuesday, 21 July 2026 Room 511C

Arts & Design

Production & Animation

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionCrafty Apes: Rendering at Scale with V-Ray

People

Sean Willis

Crafty Apes

Real-Time Live!

Create Interactive 3D Assets in Seconds!

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a live system that generates fully textured, rigged, and animated 3D assets from images in seconds. Audience members contribute prompts via their phones in real time, and their creations instantly populate a shared animated scene, demonstrating a new paradigm for interactive 3D content creation.

People

Ying-Tian Liu

Institute of Automation, Chinese Academy of Sciences

Hanxiao Wang

Creating & Iso-Surfacing SDFs - Interactive Discussion

Technical Paper

4:55pm - 5:25pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

Talks

Creating the Elemental Vortex in Avatar: Fire and Ash

4:45pm - 5:05pm PDT Tuesday, 21 July 2026 Room 403 B

Production & Animation

Research & Education

Animation

Art

Capture/Scanning

Digital Twins

Dynamics

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionThe Flux Devil, an elemental vortex in the climactic sequence of Avatar: Fire and Ash, is made of plasma, water and fire. To create an art-directable effect, while adhering to the laws of nature, we implemented specialized emission tools, warped gravity fields for buoyant updrafts and spatially varying Coriolis forces.

People

Lead FX Supervisor

Talks

Creating the scales for Gary De'Snake in Disney's "Zootopia 2"

9:40am - 10:00am PDT Thursday, 23 July 2026 Room 515 A

New Technologies

Production & Animation

Animation

Dynamics

Geometry

Industry Insight

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionCapturing the look and performance of Gary De’Snake’s scales in an appealing way was a key challenge in Disney’s “Zootopia 2”. New procedural workflows for creating and deforming scales made it possible for artists to efficiently achieve the desired look/motion while allowing for specific art-direction and exaggerated animation performance.

People

Jennifer Stratton

Jesse Erickson

Andy Milne

Brian Missey

Jose Velasquez

Creativity ≠ Generativity: A Case Study of Attentive Machine Learning in Dance Performance

Art Paper

12:05pm - 12:25pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Digital Twins

Display

Dynamics

Education

Ethics and Society

Games

Geometry

Hardware

Lighting

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionDance expresses through translation. It transforms intention and story into movement through tacit and relational knowledge. When computational systems enter, they interpret movement as machine-legible forms, shaping how dance is perceived. This paper presents a case study of human–machine co-performance translation through a movement recognition system in a twenty-minute dance work. Using wearable IMU sensors and a MiniRocket-based classifier, our system translates performers’ movements into real-time audiovisual responses, while elevating agency, care, and meaning over accuracy.

People

Ziyu Xu

University of Washington - DXARTS

Zhuodi Cai

University of Washington - DXARTS

Talks

Critical Labor History of Generative Models

5:05pm - 5:25pm PDT Tuesday, 21 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Ethics and Society

Generative AI

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

DescriptionWe introduce SIGGRAPH to critical theories of generative models, focusing on socioeconomic relations to research and art. We introduce critical theory through computing's relationship to commodification and labor and contrast two views of generative models: one as the automation of labor and another examining their role in altering human sociality.

People

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

Technical Paper

10:55am - 11:05am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionCubePart is an open-vocabulary 3D generative framework offering explicit semantic part-based control over mesh structure. Guided by a text prompt and custom part schema, it synthesizes coherent multi-part meshes, which are ready for direct integration into game engines and animation pipelines without manual post-processing.

People

Jean-Philippe Fauconnier

Educator's Forum

Current Hiring Trends in the Animation & VFX Industry

9:00am - 10:30am PDT Wednesday, 22 July 2026 Room 501 ABC

Arts & Design

Production & Animation

Research & Education

Animation

Education

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionThis panel brings together recruiting leaders from major animation and VFX studios to share first-person insight into contemporary hiring realities. Through candid discussion, panelists clarify evolving skill demands, internship and entry-level pathways, and recruitment processes, offering artists, students, and educators a clearer, more realistic snapshot of an industry in transition.

People

Computer Animation Festival

Cursed

12:30pm - 1:30pm PDT Thursday, 23 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionHedera, a mother fairy, is foretold that her daughter Pavera would be killed by a dark being. Hedera isolates her child on an island, overprotecting her, while the young girl grows more and more frustrated. After an argument between them, Pavera sees a star falling from the sky at night and runs off. She encounters Ophrys, a fairy wearing dark clothes. Hedera wakes up, finds Pavera with Ophrys and attacks the latter on sight. Pavera intervenes and both young people are killed by Hedera's last blow. Covered in ashes, Hedera realizes she is the being of the prophecy and gives up on living.

People

Director

Director

Director

Myriam Brandao Serseri

Director

Director

Director

Andrea Mamessier Degrange

Director

Director

Director

Technical Paper

Curvature Space Editing of Highly-Coiled Hair

9:30am - 9:40am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe use the material curvatures of the super-helix model to better analyze and edit tightly coiled hair. Within this curvature space, we propose novel operations for hair ruffling, heuristics for tracking flips in handedness, and control armatures that enable intuitive ensemble strand editing.

People

Alvin Shi

Florence Bertails-Descoubes

INRIA, France

A.M. Darke

University of California Santa Cruz

Theodore Kim

Curves for Technical Artists

Course

10:45am - 12:15pm PDT Sunday, 19 July 2026 Room 403 B

Production & Animation

Research & Education

Animation

Math Foundations and Theory

Full Conference Supporter

Full Conference

DescriptionThis course is an introduction to curves for technical artists and aspiring graphics engineers. We will build an understanding of curves used in computer graphics, especially rigging, from simple mathematical notation, using graphical visualisations, code implementation and relating them to their use in DCCs.

People

Thomas Stevenson

DAC & SIGGRAPH 2026 Creative Content Overview

ACM SIGGRAPH 365

11:45am - 12:45pm PDT Sunday, 19 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Education

Games

Performance

Real-Time

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis session offers a preview of SIGGRAPH 2026’s creative programming. Chairs and Directors from across the conference will share highlights from their programs, including featured projects, upcoming events, and curatorial directions. Attendees will gain an early view of how this year’s conference is expanding the role of digital art, encouraging cross-disciplinary exchange, and supporting experimentation across media, technology, and artistic practice.

The session also introduces the ACM SIGGRAPH Digital Arts Community (DAC), a platform for global dialogue among artists, designers, and technologists. Through initiatives such as SPARKS Lightning Talks, curated digital exhibitions, and student competitions, DAC connects artistic practice with computer graphics, interactive media, and emerging technologies. More information is available at dac.siggraph.org.

People

Syracuse Unievrsity

ACM SIGGRAPH Art Advisory Group

SIGGRAPH 2026 Art Papers

SIGGRAPH 2026 Computer Animation Festival

Marina Antunes

Jesse Barker

SIGGRAPH 2026 Emerging Technologies

Gerry Derksen

SIGGRAPH 2026 Immersive Pavilion

Mk Haley

SIGGRAPH 2026 Real-Time Live!

Esen K. Tütüncü

SIGGRAPH 2026 Spatial Storytelling

DAC: SPARKS in Review: Digital Art and SE Asia, Performance, Immateriality, Interabilities, Artificial Life, AI in Filmmaking, and Animism

ACM SIGGRAPH 365

1:00pm - 2:00pm PDT Monday, 20 July 2026 Room 404 AB

Arts & Design

Production & Animation

Animation

Art

Artificial Intelligence/Machine Learning

Generative AI

Performance

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis session will present the highlights from the fall 2025 and spring 2026 SPARKS (Short Presentations for the Kindred Spirit) sessions. Speakers from seven previous SPARKS session will show examples of their work and discuss the research behind their work. The "Entangled (Im)materialities" session moderated by Clea T. Waite and Bonnie Mitchell in Nov. explored artworks that challenged the structures of perception, knowledge, memory, and materiality. "Embodied Convergences: Humans, Machines, and Performance", moderated by Mona Kasra in Dec. featured artists and researchers who are redefining the possibilities of human–machine collaboration through embodied, computational, and performative practices. "Beyond the Global North: Southeast Asia’s New Wave of Generative and Interactive Innovation" moderated by Patrick Hartono and Bin You in Jan. included artists who are shaping new trajectories for generative and interactive visual culture in the SE Asia. "Interabilities in 21st Century Arts & Technology", moderated by James Hullick and Melentie Pandilovski in Feb. included neurodiverse artists who are reshaping contemporary society. "Alter Nature: Exploring Life through Computational Arts", moderated by Zi-Wei Wu in Mar. included pioneers and young artists working with the concept of artificial life. "Confluence of Generative AI and the Art of Filmmaking", moderated by Sal Ardongdé and Paul Trillo in Apr., explored how generative AI is transforming workflows and creative outcomes in the film industry. "Animism Revisited: Worlding with Digital and More-than-Human Minds", moderated by Michael Just and Gustavo Alfonso Rincon in May, considered how creative practices are reopening and complicating animist ways of sensing, valuing, and coexisting.

People

Chair

Chair

Sanglim Han

Assistant Professor

The Hong Kong University of Science and Technology (Guangzhou)

Chung-Ang University

Clea Waite

Associate Professor

Mona Kasra

Associate Professor

University of Virginia

Douglas Chan

Ardongdé Films

Patrick Lichty

Winona State University

Zi-wei Wu

Ina Conradi

Associate Professor

Mark Chavez

Data Materialization: Principles and Practices

Art Paper

5:05pm - 5:25pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Display

Education

Fabrication

Generative AI

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Robotics

Full Conference Supporter

Full Conference

Experience

DescriptionDefining data materialization is relevant because it is an emerging practice that like SIGGRAPH lies at the intersection of art and technology. Furthermore, as data collection explodes in every facet of society, data materialization offers a new form of epistemic translation--the transformation of abstract datasets into physical forms that generate meaning through material–data connections rather than informational communication.

People

Courtney Starrett

University of North Carolina Asheville

Susan Reiser

Computer Animation Festival

Dear End,

12:30pm - 1:30pm PDT Wednesday, 22 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionAn old postman goes through his last tour of deliveries in the archipelago that he worked in his whole life, gliding on water with his old bike. He finds himself confronted to the reality of his coming retirement.

People

Director

Director

Director

Director

Director

Director

Computer Animation Festival

Dear Upstairs Neighbors

12:30pm - 1:30pm PDT Thursday, 23 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionA young woman desperate for a good night’s sleep is kept awake by her exceedingly noisy neighbors. As she struggles to imagine what could be causing the cacophony upstairs, reality drifts into fantasy, and an epic battle for peace and sanity ensues.

People

Connie He

Director

Google DeepMind

Technical Paper

Deep Motion Warping via Phase-Conditioned Diffusion Autoencoder

2:30pm - 2:40pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a deep motion warping framework utilizing a phase-conditioned diffusion autoencoder. By explicitly disentangling motion into root velocity, phase, and style, it enables intuitive, high-level character animation editing including root warping, exaggeration, time warping, and style transfer while strictly preserving structural consistency.

People

Xiaogang Jin

DeepMill++: Neural Guidance Meets Rasterization for Efficient Accessibility Analysis

Technical Paper

4:25pm - 4:35pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce DeepMill++, a conservative and highly efficient framework for cutter accessibility analysis on arbitrary triangular meshes. DeepMill++ reformulates accessibility and occlusion detection as a rasterization-based visibility and depth pooling problem. DeepMill++ achieves up to 9.5× speedup over state-of-the-art geometric methods, while maintaining 97.5% conservative accessibility accuracy.

People

Emerging Technologies

Demonstrating StepDance: Redesigned CNC Machines Integrating Real-Time Control in Digital Fabrication

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a set of redesigned CNC machines for craft-aligned digital fabrication, that combine pre-planned and real-time motion control.
These machines re-envision how programmatic machine control can support a diversity of fabrication workflows, in particular demonstrating the potential for machine designers to include real-time physical input.

People

Emilie Yu

Alejandro Aponte

Ilan Moyer

Devon Frost

Maria Yang

Jennifer Jacobs

Deploying Radiance Fields Across Real-time and Web: Bridging Academia and Industry

Birds of a Feather

2:30pm - 4:00pm PDT Tuesday, 21 July 2026 Room 510

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Education

Games

Generative AI

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionThe session is for attendees interested in information exchange between the research and industry/application communities working with different implementations and applications of radiance fields.

The third community-driven forum features a panel composed of leading researchers presenting at 2026 and industry representatives, plus an audience Q&A session. It aims to foster knowledge exchange, identify future directions, and promote new collaborations, connecting the research and user communities within computer graphics and interactive techniques in applying NeRF/3DGS for visualization, digital twins, interactive media (XR/3D/web) design. The discussion will dive into data compression, web-based hosting, game engine integration, & dynamic techniques (4DGS).

People

Michael Rubloff

Radiancefields.com

Lukasz Mirocha, PhD

Hong Kong Baptist University | Opus Lab

Birds of a Feather

Designing Interfaces for Aphantasia

12:30pm - 1:30pm PDT Monday, 20 July 2026 Room 510

Research & Education

Education

Full Conference Supporter

Full Conference

Experience

DescriptionAphantasia affects how people use interfaces that assume visual memory, mental imagery, or the ability to “picture” a previous state. This Birds of a Feather session will discuss UI design patterns that make software more accessible for people who do not visualize internally: persistent previews, visible history, explicit labels, side-by-side comparisons, concrete examples, saved states, clearer spatial cues, and reduced reliance on memory-based workflows. The goal is to identify practical design guidelines for creative tools, AI tools, visualization software, and everyday applications.

People

David Shorey

Shorey Designs

Appy Hour

Developing Games as "Translation Devices" for Quantum Annealing and Validating its Social Implementation

5:00pm - 7:00pm PDT Wednesday, 22 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Games

Generative AI

Geometry

Image Processing

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis project positions game development as a "translation device" to integrate Quantum Annealing into society. It transforms abstract quantum computing into intuitive interactive experiences, validating its social implementation by bridging complex technology and human everyday perception through engaging gameplay and visuals.

People

Nobuyuki Hirai

Hitachi Consulting Co., Ltd.

Developing spatial reasoning skills using virtuality puppets

Educator's Forum

3:00pm - 3:20pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Capture/Scanning

Education

Ethics and Society

Generative AI

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis talk describes three projects based on motion tracking that help students link their intuition about the real-world to theoretical concepts, such as frames of reference and kinematics. The projects involve hands-on construction and puppetry and also allow students to show their creativity.

People

Emerging Technologies

Development of a Portable 3D Pulling Illusion System Using the 3D Vibration Motor "XReactor"

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe present XReactor, a compact motor that creates realistic 3D vibrations in any direction. Unlike traditional composite devices, its simple design provides 3d haptic sensations without complex controls. By combining it with VR, users can feel the more realistic weight and resistance of virtual objects.

People

NIDEC INSTRUMENTS CORPORATION

Masaaki Ando

NIDEC INSTRUMENTS CORPORATION

Tsuyoshi Inoue

Nagoya University

Birds of a Feather

DevOps in Production

1:00pm - 2:30pm PDT Sunday, 19 July 2026 Room 513

New Technologies

Production & Animation

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionProduction companies are often production-driven rather than engineering-driven. Because of this, they have a particularly strong need to leverage DevOps technologies and automation in order to efficiently deliver and maintain technologies within production pipelines.
This BOF will focus on recent advances in DevOps, from coding standards and workflow automation to the growing impact of AI-based workflows and tools. We are especially interested in how these technologies are being adopted in production studios and companies today.
The goal of this session is to share production-proven knowledge and tips and tricks that help improve the delivery of technologies in production environments.

People

Marc Salvati

OLM Digital, Inc.

Technical Paper

Diceplay: A Modular Canvas for Physical Image Composition

10:55am - 11:05am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionDiceplay is a modular, physical, low-resolution canvas that uses identical geometric dice to create abstract visual compositions. We propose a gradient-based optimization approach to generate Diceplay configurations from text prompts by using a novel shape grammar and relaxing the purely discrete design space to a mixed-discrete-continuous problem.

People

Milin Kodnongbua

Beijing Normal-Hong Kong Baptist University

Technical Paper

3:45pm - 3:55pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionThis paper presents a psychophysical study of dichoptic foveation, applying blur to one eye and sharpening to the other, in virtual reality. A perceptual model of interocular frequency differences across the visual field is developed and applied to enhance foveated rendering quality in VR headsets.

People

Technical Paper

Differentiable Geometry Processing & Flow Maps - Interactive Discussion

3:00pm - 3:30pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

Technical Paper

Differentiable Neutron Transport

2:50pm - 3:00pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a differentiable Monte Carlo framework for multi-energy group neutron transport, extending ideas from differentiable rendering to nuclear engineering. The method enables gradient-based sensitivity analysis and inverse design.

People

Technical Workshop

Differentiable Physics for Graphics and AI

2:00pm - 5:15pm PDT Monday, 20 July 2026 Room 406 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Digital Twins

Dynamics

Education

Fabrication

Games

Generative AI

Geometry

Industry Insight

Modeling

Physical AI

Robotics

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

DescriptionDifferentiable Physics for Graphics and AI (DPGA) is a half-day SIGGRAPH technical workshop exploring how differentiable physics-based simulation is transforming graphics and related fields including robotics, 3D vision, design, and fabrication. As simulation becomes tightly integrated with optimization, learning, and generative pipelines, differentiability enables new workflows for inverse problems, system identification, and physics-aware design.

The workshop is organized by researchers from Carnegie Mellon University, UCLA, the University of Utah, and Meta Reality Labs, whose work spans physical simulation, graphics systems, robotics, and AI. Together with invited speakers from academia and industry, they bring perspectives from foundational simulation research to large-scale production systems and real-world applications.

The workshop brings together foundational methods, practical systems, and emerging applications in differentiable simulation across graphics, robotics, 3D vision, design, and fabrication. Through keynote talks, lightning presentations, and a moderated panel, it will showcase both what differentiable physics can already enable and the technical barriers that still limit broader adoption, including efficiency, robustness, contact-rich dynamics, and the gap between application-facing representations and simulation-ready assets.

Attendees can expect an engaging forum that connects developers with researchers and practitioners seeking to use simulation as an optimization and learning primitive, not just a forward model. A key merit of the workshop is its ability to bridge communities that do not often meet in one venue, helping participants identify practical opportunities, clarify open problems, and shape future directions for differentiable simulation in graphics and AI.

People

University of Maryland College Park

Yunuo Chen

Kemeng Huang

Dewen Guo

Ying Jiang

Yifei Li

Differentiable Voxelization of Surface Representations

Technical Paper

11:35am - 11:45am PDT Monday, 20 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe provide an efficient technique to differentiate voxel values with respect to the positions of the surface that generated the voxel grid. This allows to solve problems, such as intersection detection, that can be easily solved on regular voxel grids for surface representations such as triangle meshes.

People

Technical Paper

DiffSurFlow: Efficient and Robust Differentiable Fluid Optimization via Surrogate Strategy on Flow Map

9:30am - 9:40am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present DiffSurFlow, an efficient and robust framework for long-horizon and vortex-rich fluid optimization. Powered by a physics-informed surrogate gradient strategy that exploits flow map "gradient highways" while pruning computationally intensive high-order gradient passes, it achieves significant speedups and memory reductions while maintaining near-identical gradient accuracy.

People

Yuhao Quan

Hui Wang

Weile Lian

Zhi Wang

Xubo Yang

Digital Arts Program - Combing Art and CS in a 50/50 Balance in Undergraduate Curriculum

Art Gallery

Diffusion TV

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionDiffusion TV is an interactive interface that attempts to demystify the hidden processes of AI diffusion models through a nostalgic CRT TV. By manipulating the TV’s knobs and antenna, viewers explore AI-generated images and sounds, experiencing the transformation of chaotic data into recognizable forms. Featuring three channels, Past (extinct animals), Present (endangered species), and Future (speculative AI-generated creatures), the work prompts reflection on the interconnected relationships between humanity, technology, and the environment. Through its blend of artistic interpretation and experiential AI, Diffusion TV invites audiences to consider what is preserved and what is lost in the pursuit of technological advancement.

People

Sihwa Park

York University

Educator's Forum

3:45pm - 4:05pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

Research & Education

Animation

Art

Education

Games

Scientific Visualization

Full Conference Supporter

Full Conference

Experience

DescriptionThe Digital Arts B.A. is a computer science and studio art interdisciplinary degree designed to prepare students for fields such as mobile-application and web design, game development, visual effects, interactive media, graphics, simulation, human-computer interaction and other emerging opportunities. We cover lessons learned on supporting student success in this space.

People

Brittany Morago

University of North Carolina Wilmington

Technical Paper

Digital Humans & Virtual Try-On - Interactive Discussion

9:50am - 10:15am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

Talks

Disney’s “Zootopia 2” Crowds: Bringing the Desert Festival to Life

2:20pm - 2:40pm PDT Monday, 20 July 2026 Petree D

Production & Animation

Animation

Modeling

Pipeline Tools and Work

Simulation

Full Conference Supporter

Full Conference

DescriptionIn Disney’s “Zootopia 2”, thousands of mammals gather at a Desert Festival. The expansive
layout of the set, alongside the need for art-directed performances, required an efficient,
multi-scale crowds approach. Environment-driven systems for large-scale movement,
automated placement of authored group performances, and procedural character animation, all
proved effective at scale.

People

Josh Richards

Josh Meister

Dissectible Anatomy: Embodied Exploration for Education

Real-Time Live!

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionOur technique allows us to create virtual dissectible models from color cryosection data, such as the images from the Visible Human Project, using high-performance deformable and destructible shape constraints. Models support fracture modes that are crucial to anatomy education applications: cutting, tearing and excision.

People

Technical Paper

Distance Field Rasterization for End-to-End Mesh Reconstruction

10:55am - 11:05am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionSDFRaster combines the efficiency of rasterization with signed distance fields for end-to-end mesh reconstruction from multi-view images. By optimizing a tetrahedral SDF and extracting meshes during optimization, it produces accurate, complete, and compact surfaces without heuristic post-processing.

People

Jinkai Cui

Kaiwen Song

Chumeng Niu

Juyong Zhang

Distributed Affine Body Dynamics with Adaptive Consensus

Technical Paper

11:05am - 11:15am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionAffine Body Dynamics within Incremental Potential Contact enables accurate simulation of near-rigid, extremely stiff solids with strict non-penetration. We present a distributed ABD solver based on consensus ADMM, where nodes solve local subproblems in parallel and synchronize shared bodies through global consensus, achieving robust convergence, non-penetration, and scalable multi-node performance.

People

Jiafeng Liu

Wenhui Zhou

Xinming Pei

Weiwei Xu

Divide and Truncate: A Penetration and Inversion Free Framework for Coupled Multi-physics System

Technical Paper

9:00am - 9:10am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Geometry

Hardware

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionDivide and Truncate (DAT) is a unified framework for penetration-free coupling of multi-physics systems, including rigid bodies, volumetric soft bodies, thin shells, rods, and animated objects. DAT eliminates artificial damping and deadlock issues. Material- and solver-agnostic, DAT plugs into any iterative optimizer as a post-processing step.

People

The American University in Cairo

Miles Macklin

DJM: Compact Base Meshes for Displacement Mapping using Triangle Jacobians

Technical Paper

11:05am - 11:15am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionA new method for computing base meshes for displacement mapping, exploiting the Jacobian of the displacement function to guide base-mesh computation. DJM outperforms prior art in terms of reconstruction accuracy-to-size trade off and can be used for both traditional micromesh-based rendering and neural encoding.

People

Congyi Zhang

Nicholas Vining

Yanhong Lin

TransGP

Alireza Khatami

Ziyu Sun

Xiaohu Guo

Alla Sheffer

Dog Walk: Narrating Human-AI Alignment through Companion Robots

Spatial Storytelling

10:15am - 11:00am PDT Thursday, 23 July 2026 Concourse Hall

Arts & Design

New Technologies

Art

Artificial Intelligence/Machine Learning

Generative AI

Performance

Physical AI

Real-Time

Robotics

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionBFF: Dog Walk explores human-AI intimacy through co-parenting two robot dogs. With video and live performance, the artist-researchers challenge the mind-body divide, documenting the evolution of their dogs' LLMs and their life in the intimate everyday. Blending human and machine perspectives, this project seeks a hybrid language exploring the boundaries of authenticity, embodiment, and synthetic companionship.

People

Robert Twomey

University of California, San Diego

Arthur C. Clarke Center for Human Imagination

Jesse Fleming

The Awareness Lab

Arthur C. Clarke Center for Human Imagination, UCSD

Technical Paper

DPF: Differentiable Polyphase Filtering for Large-Kernel Approximation

4:15pm - 4:25pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Games

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe introduce a novel Polyphase Filtering framework offering the fastest approximation for real-time, large-kernel image and video processing. Overcoming fixed-resolution processing constraints, our method efficiently handles complex, spatially-variant kernels. It significantly outperforms existing techniques, delivering unmatched computational speed and superior visual quality for dynamic post-processing and advanced visual effects.

People

Zhe Cao

Zhizhen Wu

Yuchi Huo

School of Informatics, Xiamen University

Zhonggui Chen

Rui Wang

DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning

Technical Paper

9:10am - 9:20am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionWe present DreamActor-M2, a universal character animation framework that regards motion conditioning as spatiotemporal in-context learning. It leverages video foundation model priors and enables end-to-end pose-free motion transfer from raw videos. Without explicit pose estimation, it achieves strong generalization and high-fidelity animation across complex scenes.

People

Mingshuang Luo

ByteDance

Institute of Computing Technology, Chinese Academy of Sciences

Institute of Computing Technology, Chinese Academy of Sciences

Hong Chang

Institute of Computing Technology, Chinese Academy of Sciences

Yong Li

School of Computer Science and Engineer, Southeast University

Art Gallery

Dreaming Babies: illi

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionDreaming Babies: illi presents 23 speculative human babies, each linked to a different chromosomal variation, sleeping and dreaming in virtual incubators in space. Using AI-generated narratives and interactive sound input, the installation invites audiences to engage with speculative futures of human birth shaped by genetic technology. Inspired by the artist’s experience with PGT, the work questions notions of “normality,” perfection, and genetic selection. Reimagining chromosomal differences not as defects but as poetic identities and superpowers, the project reframes genetic variation as a source of imagination, multiplicity, and beauty.

People

Yoon Chung Han

San José State University

Talks

Dressing the Masses - Managing Character Variations at Scale

2:00pm - 2:20pm PDT Monday, 20 July 2026 Petree D

Production & Animation

Animation

Modeling

Pipeline Tools and Work

Simulation

Full Conference Supporter

Full Conference

DescriptionTo meet the demands of massive, diverse worlds, Wardrobe decouples character design from technical rigging. By utilizing automated pipelines, it reduces manual setup from days into minutes. This system enables high-quality, scalable character variation, allowing artists to populate entire worlds while reducing technical overhead.

People

Scott Englert

Daniel Sheerin

Brian Cohen

Lillia Lai

Dual Contouring of Signed Distance Data

Technical Paper

4:25pm - 4:35pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe propose an algorithm to reconstruct explicit polygonal meshes from discretely sampled Signed Distance Function (SDF) data, which is especially effective at recovering sharp features. Building on the Dual Contouring of Hermite Data method, we solve a quadratic optimization problem to place the mesh's vertices. Critically, this optimization relies solely on discretely sampled SDF data, without requiring arbitrary access to the function, gradient information, or training on large-scale datasets. Our method sets a new state of the art in surface reconstruction from SDFs at medium and high resolutions, and opens the door for applications in 3D modeling and design.

People

University of Waterloo

Oded Stein

Technion

Dual Contouring over Expanded Cubes (DCx) for Zero-Level Set Extraction from Neural Unsigned Distance Functions

Silvia Sellán

Columbia University

Technical Paper

4:35pm - 4:45pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionDCx extends the Dual Contouring method which only extracts manifold surfaces from signed distance fields, to enable the surface extraction from unsigned distance fields. This is achieved by looking up a carefully designed table over expanded 2x2x2 cubes, allowing complex topologies to be extracted, particularly for non-manifold structures.

People

Qingchao Bao

Xuhui Chen

Dalian University of Technology

Jingpeng Yin

Wencheng Wang

Hong Qin

Stony Brook University

Nanyang Technological University (NTU)

Technical Paper

DualBrep: A Dual-Field Continuous Representation for B-rep Modelling

10:45am - 10:55am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionDualBrep presents a novel continuous representation for CAD models, resolving modeling challenges caused by heterogeneous data structures. It uses dual scalar fields: a Signed Distance Function for geometry and an Unsigned Distance Field for topology. Compressing these into a single latent space enables robust reverse engineering and generative modeling.

People

Technical Paper

Dynamic Scenes - Interactive Discussion

11:45am - 12:10pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

Technical Paper

Dynamic Visual Dominance in Stereoscopic Foveation

4:05pm - 4:15pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionThis work investigates visual dominance as a dynamic property across the FOV. Using a blur detection task, we confirm dynamic dominance in the fovea and calibrate monocular dominance in the periphery. The resulting gaze-independent peripheral dominance map can be integrated into different rendering pipelines to enhance foveation in non-dominant regions.

People

Daniel Jiménez Navarro

Hans-Peter Seidel

EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

Ana Serrano

Universidad de Zaragoza

Technical Paper

9:20am - 9:30am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionEAG-PT reconstructs indoor scenes with 2D Gaussians for editable diffuse global illumination. By separating emissive and non-emissive components and combining efficient reconstruction with path tracing, it enables more natural, physically consistent scene editing than radiance-field methods, while avoiding the geometry limitations of mesh-based inverse rendering.

People

Xijie Yang

Mulin Yu

Changjian Jiang

Kerui Ren

Tao Lu

Jiangmiao Pang

Dahua Lin

Bo Dai

Feeling AI

Linning Xu

Early Career Development: Kickstart a Career in Computer Graphics – Resume, Reel & Industry Insights

ACM SIGGRAPH 365

2:15pm - 3:15pm PDT Sunday, 19 July 2026 Room 404 AB

Research & Education

Education

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionThe ACM SIGGRAPH Early Career Development Committee (ECDC) Resume and Reel Review program has long supported students and emerging professionals through mentorship, portfolio feedback, and year-round career development programming.

In this interactive panel discussion, ECDC brings together industry professionals from fashion, enterprise visualization, infrastructure, product development, and creative technology to discuss the many pathways available within modern 3D careers beyond traditional entertainment pipelines.

Panelists include leaders working in apparel visualization, immersive media, enterprise 3D workflows, AI-assisted production, and digital product creation. Together, they will share practical insights into resumes and demo reels, hiring expectations, portfolio strategy, networking, mentorship, and adapting creative skills across evolving industries and technologies.

Rather than a traditional lecture, this session is designed as an interactive conversation shaped by audience questions and discussion. Attendees will have the opportunity to engage directly with panelists on topics including career transitions, breaking into new industries, building sustainable creative careers, and navigating the rapidly evolving landscape of 3D tools and workflows.

Whether attendees are students, emerging professionals, or experienced artists exploring new directions, this session offers an opportunity to gain real-world insight from artists and technologists actively shaping the future of 3D across multiple industries.

People

Angela Holm

Senior 3D Technical Designer

ACM SIGGRAPH – Early Career Development Committee

Angela Holm

Senior 3D Technical Designer

ACM SIGGRAPH – Early Career Development Committee

Fortune Swimwear

Michael Tanzillo

Head of 3D Tech Artists & Solution Consultants

Adobe Inc, India

Philip Luhn

Immersive Media Solutions Creative Lead

HNTB

Technical Paper

EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation

2:20pm - 2:30pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Lighting

Full Conference Supporter

Full Conference

DescriptionEasyVFX is a resource-efficient framework for high-fidelity VFX synthesis. It leverages frequency-domain decomposition to disentangle spatial detail and motion dynamics, reducing learning complexity. A frequency-aware MoE enables efficient training, while a test-time adaptation strategy refines unseen effects. The approach achieves realistic, consistent results with minimal data and computation.

People

Yue Ma

Xu Ye

Dalian University of Technology

Qinghe Wang

Yucheng Wang

Hongyu Liu

Yinhan Zhang

Fangneng Zhan

Qifeng Chen

EchoAvatar: Real-time Generative Avatar Animation from Audio Streams

Technical Paper

2:40pm - 2:50pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a novel framework designed to generate continuous, coherent full-body motion from arbitrary audio streams with low latency. Our approach is a unified streaming architecture capable of synthesizing continuous motion from incremental audio inputs. And it serves as a plug-and-play solution for transforming voice agents into interactive humanoid avatars.

People

Bohong Chen

State Key Laboratory of CAD & CG, Zhejiang University

Yumeng Li

State Key Laboratory of CAD & CG, Zhejiang University

Yinglin Xu

State Key Laboratory of CAD & CG, Zhejiang University

Youyi Zheng

State Key Laboratory of CAD & CG, Zhejiang University

Yanlin Weng

State Key Laboratory of CAD & CG, Zhejiang University

Kun Zhou

State Key Laboratory of CAD & CG, Zhejiang University

Art Paper

Echoes of the Prior: A Computational Phenomenology of Forgetting

3:45pm - 4:05pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Display

Education

Fabrication

Generative AI

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Robotics

Full Conference Supporter

Full Conference

Experience

DescriptionEchoes of the Prior visualizes entropy within neural networks, turning machine forgetting into an interactive 4D experience. Unlike traditional CG simulating physical reality, this work reveals the aesthetics of algorithmic degradation, transforming technical failure into a new artistic medium bridging AI explainability with philosophical inquiry. It challenges the community to look beyond high-fidelity reconstruction and embrace the fragility of intelligence, proposing that data dissolution is as significant as its preservation.

People

Gege Gao

University of Tuebingen

Max Planck Institute for Intelligent Systems

Bernhard Schölkopf

Eclipsed Bokeh: A Conceptual Model for Defocusing Through Defocused Edges

Andreas Geiger

University of Tübingen

Tübingen AI Center

Talks

9:40am - 10:00am PDT Sunday, 19 July 2026 Room 403 B

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Computer Vision

Digital Twins

Education

Games

Image Processing

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionA defocused object viewed through the edge of another defocused object exhibits strange warping and reshaping effects, known as “eclipsed bokeh”. By studying what happens to the bokeh, we can see how to recreate the effect from 2D images.

People

Christopher Berry

Framestore

Art Paper

Edges of Immersion: Data Translation into Ecoaesthetic Experience

10:00am - 10:20am PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Research & Education

Animation

Art

Audio

Augmented Reality

Capture/Scanning

Dynamics

Hardware

Lighting

Performance

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionClimate knowledge is increasingly shaped by complex data that remain experientially distant. This paper examines how immersive ecoaesthetic practices translate environmental data into situated sensory experience. Through a case study, it introduces edges of immersion, showing how artistic strategies make mediation perceptible and enable new ways of engaging with climate imaginaries.

People

Rasa Smite

ZHdK Zurich University of the Arts

RIXC Center for New Media Culture

Raitis Smits

Art Academy of Latvia

RIXC Center for New Media Culture

Educator's Forum

Educator's Townhall Session

12:30pm - 1:30pm PDT Thursday, 23 July 2026 Room 409 AB

Full Conference Supporter

Full Conference

Experience

DescriptionAfter four days of education-focused presentations, attendees are invited to an invigorating, open discussion on current topics in computer graphics education and interactive techniques. Come to the town hall session to ask questions, share perspectives, and have a good time with the SIGGRAPH education community!

Technical Workshop

Efficient 3D Content Creation for Immersive Experiences

2:00pm - 5:15pm PDT Tuesday, 21 July 2026 Room 406 AB

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Computer Vision

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionThis workshop is dedicated to democratizing 3D content creation, encompassing both static and dynamic 3D assets, by exploring cutting-edge advances in volumetric video built on 4D Gaussian Splatting, fast 3D objects and scenes reconstruction, AI generated 3D content, and real-time immersive video generation with diffusion models.
We bring together both academic and industrial researchers and practitioners to discuss scalable pipelines that lower the barrier to immersive content creation. What's more, we will explore the 3D/4D content experience on both VR headsets as well as consumer mobile platforms.
A key feature of this workshop is a hands-on demonstration: participants will experience 1) volumetric video of industrial demonstration in both video-on-demand applications and in real-time streaming of
live-broadcasting, 2) interactive experience of AI generated 3D content and 3D reconstruction, and also 3) real-time interactive and high-resolution video generation via diffusion models.
The workshop seeks to bridge the gap between cutting-edge 3D content creation in academic research and in real-world industrial applications.

People

Efficient B-Spline Finite Elements for Cloth Simulation

Technical Paper

11:25am - 11:35am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a quadratic B-spline FEM approach for cloth simulation that captures smoother, more accurate deformations with rich wrinkle detail and few artifacts. Our optimized reduced integration scheme enables better performance compared to traditional linear FEM, while supporting robust, high-quality cloth simulation for realistic garment animation.

People

Yuqi Meng

Yihao Shi

Kemeng Huang

Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation

Technical Paper

9:40am - 9:50am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a hybrid framework for rendering dense hair and fur. By preserving fine geometric details for direct illumination while approximating complex multiple scattering within an equivalent anisotropic volume, our method achieves path-traced visual fidelity and soft glow of multiple scattering at a drastically reduced computational cost.

People

Shandong Universityong

Technical Paper

Efficient Multiscale Lanczos Eigenpair Extraction

9:20am - 9:30am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe extend the implicitly restarted Lanczos method to a multiscale context using arbitrary multigrids (algebraic, geometric) and we demonstrate the gain in performance and robustness on a variety of application scenarios.

People

Theo Braune

Centre National de la Recherche Scientifique - Laboratoire d'informatique de l'École Polytechnique (LIX)

Technical Paper

Efficient Sampling: ReSTIR and More - Interactive Discussion

10:00am - 10:30am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Full Conference Supporter

Full Conference

Technical Paper

EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

4:25pm - 4:35pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionEgoForce enables real-time 3D hand pose, shape, and absolute position recovery from a single head-mounted RGB camera. Designed for lightweight smart glasses, it uses forearm cues and camera-aware ray-space lifting to provide precise tracking across diverse camera models and device setups.

People

Christen Millerdurai

DFKI

EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering

Technical Paper

3:55pm - 4:05pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Fabrication

Haptics

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionTo enable seamless mixed-reality telepresence in the wild, we present EgoRelight, a robust human performance capture and HDR illumination recovery approach using a single portable head-mounted device. This dual capability drives the photorealistic and relightable full-body 3D avatars, blending users naturally into surrounding environments.

People

Jianchun Chen

Saarbrücken Research Center for Visual Computing, Interaction and AI

Saarbrücken Research Center for Visual Computing, Interaction and AI

Christian Theobalt

Saarbrücken Research Center for Visual Computing, Interaction and AI

Computer Animation Festival

Games Summit

Einvala

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionIn an age long past, where gods and mortals coexisted in fragile harmony, Bjorn, a valiant Viking warrior, is entrusted with a sacred mission. Guided by the ancients, he must recover the fragments of the Astral Stone, a divine artifact shattered during the fall of the old realms. Across lands ravaged by chaos and haunted by forgotten creatures, Bjorn faces dark forces to restore balance to the worlds and save his tribe from a grim fate.

People

Director

Director

Director

Alex Mongkhounepraseuth

Director

Director

Director

Director

Director

Director

Director

Art Paper

Electrospun Fields: 3D Nano-Fiber Material Computation as Design Method

4:05pm - 4:25pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Display

Education

Fabrication

Generative AI

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Robotics

Full Conference Supporter

Full Conference

Experience

DescriptionElectrospun Fields advances SIGGRAPH’s interest in material computation by framing electric fields as programmable boundary conditions and fiber deposition as a material rendering of invisible forces. It contributes a reproducible UR20 robotic workflow for non-planar electrospinning, enabling ultra-light 3D membranes difficult to achieve with planar setups. By linking conductive scaffold topologies to material behaviors using bio-compatible polymers, this framework opens novel pathways for emergent and expressive computational art and fabrication.

People

Justin Wan

Ayah Mahmoud

Sergio Mutis

Avantika Velho

Zhiyan Xing

Media Lab, Massachusetts Institute of Technology (MIT)

Behnaz Farahi

Embodiment and Translation - Q&A

Art Paper

12:25pm - 12:35pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Digital Twins

Display

Dynamics

Education

Ethics and Society

Games

Geometry

Hardware

Lighting

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAfter all the presentations, attendees are invited to participate in a Q&A.

Emerging Technologies

EmerFlux: A Two-Layer Liquid Surface Display for Organic Pixel-Based Aesthetic Representation of Information

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionEmerFlux is a two-layer liquid surface display that renders dynamic protruding pixels at the water–oil interface. By independently controlling an 11×11 pump array, it enables organic dot-based patterns and fluid aesthetic expressions directly on a living liquid surface.

People

Emerging Technologies

Technical Paper

Emerging Technologies Demo - A Generalizable Light Transport 3D Embedding for Global Illumination

3:50pm - 4:50pm PDT Wednesday, 22 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
A Generalizable Light Transport 3D Embedding for Global Illumination

We introduce a scalable 3D embedding that learns global illumination directly from 3D scene configurations. This design scales to environments with millions of triangles, enabling the first generalizable GI learning on complex, high-fidelity indoor scenes, far beyond prior limits. It bypasses per-scene retraining and screen-space artifacts to deliver realistic rendering.

Paper Presentation Presented: Tuesday, July 21, 2-3:30 pm; Paper Session: Light Transport; Room 408 A

People

Bing Xu

Emerging Technologies Demo - A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction

Emerging Technologies

Technical Paper

2:40pm - 3:40pm PDT Tuesday, 21 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction

Gaussian Splatting struggles with large scenes due to memory limits and chunking artifacts. We introduce "A LoD of Gaussians," a new framework enabling ultra-large scene training and rendering on a single consumer GPU. Through out-of-core streaming and Level-of-Detail, it achieves seamless multi-scale reconstruction without relying on scene partitioning.

Paper Presentation Presented: Monday, July 20, 2-3:30 pm; Paper Session: 3D Gaussian Splatting I; Room 408 A

People

Felix Windisch

Emerging Technologies Demo - Abstraction in Style: Beyond Texture and Color

Emerging Technologies

Technical Paper

1:30pm - 2:30pm PDT Wednesday, 22 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
Abstraction in Style: Beyond Texture and Color

Artistic styles often involve shape reinterpretation, not merely a change of surface appearance. Conventional style transfer methods miss this deeper abstraction behavior. We introduce Abstraction in Style (AiS), a two-stage generative framework that learns and transfers style at shape level, beyond texture and colors, enabling more expressive and controllable stylization.

Paper Presentation Presented: Thursday, July 23, 9-10:30 am; Paper Session: NPR, Style & Abstraction; Room 408 B

People

Hui Huang

Shenzhen University

Emerging Technologies

Technical Paper

Emerging Technologies Demo - AGILE: Hand-object Interaction Reconstruction from Video via Agentic Generation

3:50pm - 4:50pm PDT Tuesday, 21 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
AGILE: Hand-object Interaction Reconstruction from Video via Agentic Generation

AGILE reconstructs 3D hand-object interactions from monocular videos via agentic generation. It produces complete, simulation-ready object meshes and robustly estimates object pose without SfM, enabling accurate and stable results on challenging real-world data.

Paper Presentation Presented: Monday, July 20, 3:45-5:35 pm; Paper Session: Humans & Hands - Reconstruction; Room 403 A

People

Hao Chen

Emerging Technologies Demo - EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

Emerging Technologies

Technical Paper

10:00am - 11:00am PDT Tuesday, 21 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

EgoForce enables real-time 3D hand pose, shape, and absolute position recovery from a single head-mounted RGB camera. Designed for lightweight smart glasses, it uses forearm cues and camera-aware ray-space lifting to provide precise tracking across diverse camera models and device setups.

Paper Presentation Presented: Monday, July 20, 3:45-5:35 pm; Paper Session: Humans & Hands - Reconstruction; Room 403A

People

Christen Millerdurai

DFKI

Emerging Technologies

Technical Paper

Emerging Technologies Demo - GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse Smoke Reconstruction

10:00am - 11:00am PDT Wednesday, 22 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse Smoke Reconstruction

We present a physics-aware method for reconstructing dynamic fluids from sparse-view videos. By integrating volumetric rendering with physically guided Gaussian optimization, it enforces consistency in density and motion, reducing artifacts and improving realism. The approach achieves accurate, stable 3D smoke reconstruction with high visual and physical fidelity.

Paper Presentation Presented: Tuesday, July 21, 9-10:30 am; Paper Session: Fluid Reconstruction & Optimization; Room 408 A

People

Ren Bo

Nankai University

Emerging Technologies

Technical Paper

Emerging Technologies Demo - LightOpt: Lights Optimization for Real-time Rendering

11:10am - 12:10pm PDT Tuesday, 21 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
LightOpt: Lights Optimization for Real-time Rendering

LightOpt is a differentiable optimization framework that automatically reduces the number of lights in real-time game scenes while preserving visual appearance. By optimizing and restructuring real-time light sources, it lowers lighting cost, reduces overlap, and improves cross-platform performance for modern game rendering.

Paper Presentation Presented:
Monday, July 20, 3:45-5:15 pm; Paper Session: Real-Time Rendering; Room 408 A

People

Luyan Cao

Emerging Technologies Demo - LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization

Emerging Technologies

Technical Paper

12:20pm - 1:20pm PDT Wednesday, 22 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization

LooseRoPE enables prompt-free image editing by letting users crop and paste objects directly into new scenes. It improves diffusion-based harmonization by modulating RoPE with saliency, balancing identity preservation and contextual blending. This yields intuitive, spatially precise edits that maintain object appearance, pose, and placement without requiring text prompts or masks.

Paper Presentation Presented: Thursday, July 23, 10:45 am-12:15 pm; Paper Session: Image Editing,; Room 408 B

People

Etai Sella

Tel Aviv University

Emerging Technologies

Technical Paper

Emerging Technologies Demo - MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives

11:10am - 12:10pm PDT Wednesday, 22 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives

MotionBricks is a real-time generative framework that transforms interactive motion control for animation and robotics. By combining a large-scale latent backbone with intuitive "smart primitives," it delivers high-quality, zero-shot motion synthesis at 15,000 FPS, allowing users to effortlessly build complex and fine-grained animations and robotic applications.

Paper Presentation Presented: Tuesday, July 21, 2-3:30 pm; Paper Session: Motion Generation, Warping & Control; Room 403 A

People

Tingwu Wang

Emerging Technologies Demo - MUSIC: Learning Muscle-Driven Dexterous Hand Control

Emerging Technologies

Technical Paper

12:20pm - 1:20pm PDT Tuesday, 21 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
MUSIC: Learning Muscle-Driven Dexterous Hand Control

We present a data-driven framework for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform piano playing for novel musical scores. Our framework adopts a hierarchical architecture, combining high-frequency muscle control with low-frequency coordination. The method achieves coordinated bimanual motions and produces human-like activation patterns, generalizing beyond reference data.

Paper Presentation Presented: Thursday, July 23, 2-3:30 pm; Paper Session: Learning in Motion; Room 403 A

People

Pei Xu

Emerging Technologies Demo - Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects

Emerging Technologies

Technical Paper

1:30pm - 2:30pm PDT Tuesday, 21 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects

Sketch2Arti is the first sketch-based articulation modeling system for CAD objects. Given a CAD model and simple 2D sketches, it identifies movable parts and predicts motion parameters. It can also complete missing internal structures revealed by motion, enabling controllable, iterative, and generalizable articulation modeling for diverse objects.

Paper Presentation Presented: Wednesday, July 22, 10:45 am-12:35 pm; Paper Session: Vectors Graphics, Strokes & Sketches; Room 403 A

People

Changjian Li

EmoMime: Augmenting Social Behavior and Self-Expression via Wearable Robotic Limbs

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionEmoMime is a neck-mounted wearable robotic system designed to augment social behavior and self-expression. Utilizing a soft-rigid hybrid structure, it enables safe, expressive interactions near the user's face. We invite attendees to experience how a human-like robotic hand near the face dynamically amplifies social signals and enables comforting self-touch.

People

Hideki Shimobayashi

Tokyo University of Science

Tomoya Sasaki

Masaharu Hirose

Arata Horie

commissure Inc.

Masahiko Inami

Emotion Manipulation for Talking-Head Videos via Facial Landmarks

Technical Paper

2:10pm - 2:20pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionPreserving lip synchronization during emotion manipulation in video is a major challenge. This paper proposes a method using a pretrained StyleGAN and a latent-based landmark editing module. It modifies the latent edit direction with facial landmarks, enabling fast, high-quality emotion changes while sustaining original lip sync.

People

KAIST, Visual Media Lab

Kwanggyoon Seo

Flawless AI

Emerging Technologies

EnableController: Generative Kinematics for Universal Access and Gamified Rehabilitation

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionEnableController democratizes gaming accessibility by transforming the human body into a universal input device. Using Generative AI to translate natural language into kinematic controls, and virtual emulation for compatibility, it allows users with disabilities to play any commercial game using therapeutic or comfortable body movements—no coding required.

People

Educator's Forum

Engineering Empathy: A Blueprint for Interdisciplinary Art and Engineering in K-12 Education

10:45am - 11:05am PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Computer Vision

Digital Twins

Education

Games

Modeling

Pipeline Tools and Work

Rendering

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionLimbitless ENGAGE dismantles educational silos through human-centric bionics. This scalable STEAM framework integrates digital arts, game design, and engineering via "near-peer" mentorship. Students utilize a replicable "Bionic Blueprint" to master graphics for social impact, empowering the next generation to design for humanity through empathy-driven, interdisciplinary collaboration.

People

Matt Dombrowski

Peter Smith

Albert Manero

Emely Benjamin

Enhancing Immersive Exergames through Reflection-In-Action through Voice Encouragement via LLM

Immersive Pavilion

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis study introduces a real-time feedback system for VR exergames. By leveraging LLMs to analyze personal movement data against historical datasets , the system provides personalized voice encouragement to support reflection-in-action and aim to enhance players' performance.

People

Zong-Ying Li

Yen-Hua Lai

Yun-Ru Hsu

National Taipei University of Education

Chien-Hsing Chou

Tse-Yu Pan

National Taiwan University of Science and Technology

Ping-Hsuan Han

Envoxel: Live Environment Generation for Voxel Worlds

Appy Hour

5:00pm - 7:00pm PDT Wednesday, 22 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Games

Generative AI

Geometry

Image Processing

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionEnvoxel is an interactive voxel environment and structure generation app. It turns prompts into editable block structures, preserving interiors and materials while streaming predictions live in the browser. The demo shows upload, cut, completion, side-by-side inspection, and export for game-native voxel worlds.

People

Ryan Hardesty Lewis

Evolution of Anatomy at Framestore

Talks

12:05pm - 12:25pm PDT Monday, 20 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Dynamics

Games

Generative AI

Geometry

Modeling

Performance

Pipeline Tools and Work

Real-Time

Simulation

Full Conference Supporter

Full Conference

DescriptionFramestore introduces the Anatomy Toolkit (FAT), replacing legacy deformer workflows with an end-to-end simulation platform. FAT automates constraint construction through geometric labeling and enables the convergence of Rigging and Creature FX workflows. This delivers anatomically accurate, high-fidelity muscle and tissue deformations with superior efficiency and simplified artist experience.

People

Christoph Genzwuerker

Technical Paper

Exact predicates, exact constructions and combinatorics for mesh CSG

10:45am - 10:55am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis article introduces an algorithm that exactly constructs the so-called Weiler model (also called a 3D mesh arrangement) and that uses it to implement CSG with arbitrary multi-operand expressions. The main contribution is a 2D Constrained Delaunay Triangulation with exact coordinates and symbolic perturbations to disambiguate configurations with co-cyclic points.

People

Bruno Levy

Inria Saclay and Laboratoire de Mathématiques d'Orsay Université Paris Saclay

Bruno Levy

INRIA, Saclay; Centre Inria de Saclay

Exhibition

10:00am - 5:00pm PDT Tuesday, 21 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionVisit the Exhibition

Computer Animation Festival

Exit

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionNorah, a seasoned war correspondent, is living with cancer. Determined to make the most of the time she has left, she turns to Nadim, her closest friend and former cameraman, to join her for one final assignment.

People

Victor Watier-Berthiaume

Director

No affiliation

Jérémie Dagenais

Director

No affiliation

Art Paper

Expanded Voices: Voice Cloning, Latent Spaces, and Embodied Translation

11:05am - 11:25am PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Digital Twins

Display

Dynamics

Education

Ethics and Society

Games

Geometry

Hardware

Lighting

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis work treats AI models not only as technical systems, but as perceptual, embodied, and cultural artifacts. By combining voice cloning and latent space visualization in an interactive installation, the project demonstrates how AI representations can become accessible and critically examined. It opens new perspectives on translation, embodiment, and authorship, offering artists, researchers, and technologists a shared framework to reflect on how computational representations shape creative practice and human identity.

People

Tomas Andrade Weber

Maria Arnal Dimas

Raquel Barrachina Llobet

Sol Bucalo Mana

Jerónimo Calderón

Fernando Cucchietti

Thaleia Ntiniakou

Adrià Espinoza Gómez

Paula Fernández Vergara

David Garcia-Povedano

Alex Gil

Roger Gonzalez March

Othmane Hayoun Mya

Marc Heras Villacampa

Míriam Herrero-Valea

Guillermo Marín

Paula Méndez Gordillo

Sara Tolosa Alarcón

Experience Presentation: Artist Talks

Art Gallery

10:30am - 12:30pm PDT Wednesday, 22 July 2026 Room 404 AB

Full Conference Supporter

Full Conference

Experience

DescriptionThis Experience Presentation: Artist Talks session brings together SIGGRAPH 2026 Art Gallery artists and curated contributors to explore In-Betweens: the technical, conceptual, temporal, and spatial relations that emerge across systems, materials, bodies, environments, and publics. Spanning interactive installation, AI, robotics, bio-art, data portraiture, ecological simulation, digital printmaking, and experimental animation, these talks offer a behind-the-scenes view into the creative processes and critical questions shaping contemporary technologically mediated art.

Artist Talks:
1. Sternwerk — Alvaro Cassinelli, Tobias Klein
2. 顫杵 sensho — Ryuichi Ono, Tetsuaki Baba
3. A Walled City — Weidi Zhang, Rodger Luo
4. in-between: home, belonging, and the Asian diaspora — Shirley Wu
5. Are We Gazing at the Same Moon? — Jeyun Cloud, Ziqian Yin
6. SOMA: In Search of Somatic Intelligence — Pinyao Liu
7. Stuck in the Middle — Avital Meshi
8. Gradi — Joey Verbeke, Koi Ren
9. Diffusion TV — Sihwa Park
10. Dreaming Babies: illi — Yoon Chung Han
11. Simulacra Naturae - Entangled Biomes — Nefeli Manoudaki, Iason Paterakis, Mert Toka, Diarmid Flatley, Stejara Dinulescu
12. The Long Fall: A Descent Into the Ocean's Living Memory — Jiabao Li, Will Tallent
13. David Em Print Exhibition — Catharina Santasilia
14. 2025 Ars Electronica Animation Festival — Juergen Hagler

Immersive Pavilion

Experience Presentation: Immersive Pavilion- How Human Sensation Shapes XR Experiences

4:00pm - 4:45pm PDT Monday, 20 July 2026 Concourse Hall

New Technologies

Research & Education

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionMixed reality experiences often have human interaction at the center of their design and implementation. At SIGGRAPH 2026, the Immersive Pavilion has even more contributed pieces with elements of human sensation or interaction than years previous. Explore how the ever-changing landscapes of XR technology allow for more advanced human-centered design at this panel discussion with our esteemed contributors from this year's Immersive Pavilion.

Smileoyed: Embodied Virtual Pet for Behavioral Affective Synchrony with Multisensory and Biofeedback
Ping-Hsuan Han
National Taipei University of Technology

Exploring Attention States and Narrative Engagement in an Interactive VR Experience
Samantha Lai
Carnegie Mellon University

Landmine/Garden
Haoren Zhong
NYU ITP

MoveTogether: Exploring Physical Co-op Gameplay in Co-located Mixed Reality via Modular Shared Props
Zi-Yun Lai
National Taiwan University

Emerging Technologies

Experience Sharing Studio: An Immersive Platform for Spatio-Temporal Recording and Playback of Embodied Multisensory Memory

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionExperience Sharing Studio (ESS) lets visitors relive recorded human experiences through synchronized spatial video, sound, haptics, floor feedback, and 3D poses. Using the Experium Platform and unique Experience IDs, ESS connects audiovisual and embodied information into interactive playback. Visitors can explore both dynamic actions and quiet moments at their own pace through the Spatio-Temporal Progress Bar and User-Driven Playback Mode.

People

Haruomi Higashi

Yufan Zhu

Musashino Art University Imaging Arts and Sciences

Kohei Kobayashi

Kiryu Tsujita

Jinsuke Morita

Emi Koizumi

Jiayi Shen

Mauricio Sousa

Arata Horie

commissure Inc.

Takatoshi Yoshida

Kouta Minamizawa

Explicit flows for implicit surfaces

Technical Paper

2:30pm - 2:40pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionOur paper presents a method for shape-morphing and deformation using an exact mathematical flow. We introduce a neural architecture guaranteed to encode a flow, leveraging implicit supervision of explicit flows, ensuring topological consistency and efficient forward/inverse computation without ODE solvers. Applications include shape-morphing, editing, and transitions via a reference shape.

People

Immersive Pavilion

Exploring Attention States and Narrative Engagement in an Interactive VR Experience

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionA neuro-interactive installation merging cinema and neuroscience. Using EEG and gaze tracking, this exhibition monitors the audience's live attentional shifts during implicit narrative choices. Participants can gain insights into their own brain states as they transition from passive observers to active agents as they engage in an implicitly interactive narrative experience.

People

Samantha Lai

Vivian Shen

Exploring Quantum Computing for Texture Generation

Talks

3:00pm - 3:20pm PDT Wednesday, 22 July 2026 Room 515 A

Arts & Design

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Games

Generative AI

Industry Insight

Lighting

Modeling

Physical AI

Pipeline Tools and Work

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionThis talk introduces a novel framework that bridges ray tracing and quantum physics. We use Quantum Collision Models to simulate materials with optical properties that dynamically evolve in response to light. This enables the synthesis of new materials with complex optical signatures, suitable for production pipelines and near-term quantum hardware.

People

Technical Paper

Fabrication - Interactive Discussion

4:55pm - 5:25pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

FabricTryOn: Taming Image Editing Models for Garment Re-Texturing

9:00am - 9:10am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionWe study fabric try-on as a garment re-texturing task, replacing fabric materials while preserving garment geometry and illumination. Leveraging modern image editing models and a real-image data curation pipeline, our framework performs fabric removal and application directly in image space, enabling coherent and photorealistic fabric try-on from a single image.

People

Jun Ma

Style3D Research

Qian He

Style3D Research

Xiaogang Jin

Face Rigging through Curvenet Parametrization

Talks

10:45am - 11:05am PDT Monday, 20 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Dynamics

Games

Generative AI

Geometry

Modeling

Performance

Pipeline Tools and Work

Real-Time

Simulation

Full Conference Supporter

Full Conference

DescriptionWe describe a new rigging technique that generates face parametrizations by leveraging curvenets as a sparse proxy for authoring weights outlining face contours, which are then interpolated across the surface mesh to drive face articulation. We showcase our method using face rigs built for various characters from Disney/Pixar’s Hoppers.

People

Jeremie Talbot

WilliamS Sheffler

Fernando de Goes

Faces & Avatars - Interactive Discussion

Technical Paper

3:00pm - 3:30pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Fast and Accurate Gaussian Process Modelling of Real-World Materials

11:15am - 11:25am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose a BRDF modeling method that provides accurate and compact representations for isotropic and anisotropic BRDFs. We propose new theoretical developments enabling tractable Gaussian Process BRDF regression, leading to analytical BRDF representations. State-of-the-art methods can be outperformed in most BRDF cases by using a small training set of observations.

People

Arnau Colom

Pompeu Fabra University Interactive Technologies Group (GTI)

Christian Bouville

Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)

Julien Pettre

Institut National de Recherche en Informatique et en Automatique (INRIA) Rennes University, CNRS, IRISA

Kadi Bouatouch

Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)

Ricardo Marques

Pompeu Fabra University Interactive Technologies Group (GTI)

Arnau Colom

Pompeu Fabra University, Interactive Technologies Group (GTI)

Technical Paper

Fast and Exact Winding Numbers for Triangle Meshes

10:45am - 10:55am PDT Monday, 20 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionGeneralized winding numbers are a useful measure for inside-outside classification. This paper introduces a novel method for computing winding numbers for triangle meshes, which leverages a ray-mesh intersection and an elementary sum over boundaries. Our algorithm gives the exact answer and is more efficient than all existing techniques in practice.

People

Peiyuan Xie

Christian Hafner

Chris Wojtan

Fast Sparse Matrix Permutation for Mesh-Based Direct Solvers

Technical Paper

3:55pm - 4:05pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a fast sparse matrix permutation algorithm tailored to mesh-based direct solvers. By exploiting mesh structure through patch-based nested dissection, our method reduces permutation overhead while preserving high-quality orderings, leading to substantial end-to-end speedups in sparse Cholesky factorization on both CPUs and GPUs.

People

Behrooz Zarebavani

Ahmed Mahmoud

Changcheng Yuan

Serban Porumbescu

John Owens

Maryam Mehri Dehnavi

Fast VEM Fluid Simulation

Technical Paper

9:20am - 9:30am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionFastVEM is an efficient boundary-conforming fluid simulation framework. It combines Virtual Element discretization, a simulation-friendly body-fitted grid construction strategy, and a tailored geometric multigrid method to achieve robust, high-fidelity, and efficient fluid–boundary interaction.

People

Talks

Fast, High-Volume Asset Imports and Exports Using Unreal Engine and OpenUSD

9:00am - 9:20am PDT Sunday, 19 July 2026 Petree D

Production & Animation

Animation

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

DescriptionWe present a scalable workflow for importing and managing film production environment assets. By using Unreal Engine and OpenUSD, this workflow reduces import times, load times, and data footprints while improving framerate. This avoids traditional DCC geometry overhead and allows teams to rapidly import polygon-dense assets with increased interactive performance.

People

Tzung-da Tsai

Darian Wang

Manuel Agost Garcia

Jason Baldwin

Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification

Technical Paper

2:10pm - 2:20pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a structure-aware densification method for 3D Gaussian Splatting that adapts primitives based on local texture frequency. By combining multi-scale analysis and anisotropic splitting, it preserves fine details while avoiding unnecessary density, enabling faster training and higher-quality novel view synthesis.

People

Linjie Lyu

Ayush Tewari

Cambridge University

Jianchun Chen

Thomas Leimkuehler

Christian Theobalt

Feature-Preserving Offset Meshing

Technical Paper

11:15am - 11:25am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis paper introduces a novel method for generating offset meshes from 3D surfaces. It uniquely supports mitered joins and variable offset distances while robustly preserving sharp features. Evaluated on a broad dataset, our approach outperforms state-of-the-art methods in feature fidelity and element count.

People

Hongyi Cao

Gang Xu

Renshu Gu

Jinlan Xu

Beijing Institute of Spacecraft System Engineering

Xiaoyu Zhang

Rabczuk Timon

Bauhaus University Weimar

Yuzhe Luo

State Key Laboratory of CAD&CG Zhejiang University

Xifeng Gao

LightSpeed Studios

Hongyi Cao

Hangzhou Dianzi University, City University of Hong Kong

Technical Paper

Film/VFX Production - Interactive Discussion

2:50pm - 3:20pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Lighting

Full Conference Supporter

Full Conference

Technical Paper

Finding Fast Filters

2:50pm - 3:00pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

DescriptionImage and audio processing applications want to use large FIR filters while adhering to strict runtime and latency requirements. Prior methods for fast filter approximation offer limited speed versus quality tradeoffs. We unify these approximation techniques as primitives within an automatically searchable space for fast 1D and 2D filters.

People

Jonathan Ragan-Kelley

Massachusetts Institute of Technology - EECS

Karima Ma

Adobe Inc

Stage Session

Fine-Tuning Neural Graphics Models with Arm Model Gym

1:00pm - 1:30pm PDT Wednesday, 22 July 2026 West Hall A

Gaming & Interactive

Artificial Intelligence/Machine Learning

Computer Vision

Games

Generative AI

Graphics Systems Architecture

Hardware

Image Processing

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Spatial Computing

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionIntroduces Arm’s Neural Graphics
Model Gym as a practical workflow for
adapting neural graphics models, with NFRU
as the core example. Developers will see
PyTorch and Jupyter-based configuration,
fine-tuning, evaluation, visual comparisons,
TensorBoard metrics, Model Explorer graph
inspection, and export to .vgf for Arm’s
Vulkan ML deployment path.

People

Gabriel Peterson

Arm

Technical Paper

FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On

2:50pm - 3:00pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce FIT (Fit-Inclusive Try-on), a virtual try-on dataset of over 1M samples covering diverse garment fits, each annotated with precise body/garment measurements. Our novel data generation pipeline leverages synthetic garment simulation and photorealistic retexturing. Then, we leverage FIT to train a state-of-the-art fit-aware virtual try-on model.

People

Yuanhao Wang

Johanna Karras

Yingwei Li

Ira Kemelmacher-Shlizerman

FLASHand: Feed-forward reLightable and Animatable Single-view Hand Reconstruction

Technical Paper

4:05pm - 4:15pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe propose FLASHand, the first feed-forward model to reconstruct high-fidelity, relightable, and animatable 3D hand avatars from a single RGB image. By leveraging NIMBLE priors and mesh-based 2D Gaussian Splatting, FLASHand achieves instant, personalized reconstruction with disentangled appearance, supporting real-time animation and relighting.

People

Ling-Xiao Zhang

Institute of Computing Technology, Chinese Academy of Sciences

Institute of Computing Technology, Chinese Academy of Sciences

Lin Gao

South China University of Technology

Wei-Hong He

Yu-Xuan Yang

East China Normal University

Yunbing Xing

Institute of Computing Technology, Chinese Academy of Sciences

Yu-Kun Lai

Cardiff University

Yiqiang Chen

Institute of Computing Technology, Chinese Academy of Sciences

Spatial Storytelling

Flashover: Spatial Storytelling of Wildfire from Memory to Spatial Experience

11:15am - 12:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Production & Animation

Research & Education

Capture/Scanning

Image Processing

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe present Flashover, a spatial storytelling project that reframes wildfire as lived experience: memory, repetition, and loss. We describe how multi-zone installation design and point-based volumetric imagery invite active perception rather than spectacle, translating traumatic memory into embodied encounter and reflection on the climate crisis.

People

Phillip Wilkinson

University of Melbourne

Robert Ellis Walton

University of Melbourne

SeungWon Jeong

University of Melbourne

Taehyun Rhee

University of Melburne

Technical Paper

Flatten the Complex: Joint B-Rep Generation via Compositional k-Cell Particles

11:15am - 11:25am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionGenerating CAD B-Reps is challenging due to complex topology-geometry entanglement. We solve this by reformulating B-Reps into compositional k-cell particles. Our flow matching framework unifies topological entities, enabling the joint generation, precise 3D reconstruction, and local in-painting of high-fidelity CAD models with superior validity.

People

Junran Lu

Yuanqi Li

Hengji Li

Jie Guo

Yanwen Guo

Floating-Point Robustness in Parametric Surface Continuous Collision Detection: From Algorithm to Benchmarking

Technical Paper

9:30am - 9:40am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Geometry

Hardware

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present solutions to the floating-point–induced decision errors arising in CCD for parametric surfaces, including an error-resistant CCD method and a data construction pipeline with known GT for algorithm evaluation under floating-point perturbations. Experimental results demonstrate that the proposed methods are effective and robust.

People

Xuwen Chen

SIST, Peking University

Junyu Wang

Southeast University

Cheng Yu

SIST, Peking University

Xingyu Ni

Nanjing University of Science and Technology

Meng Zhang

State Key Laboratory of General Artificial Intelligence

Baoquan Chen

Fluid Reconstruction & Optimization - Interactive Discussion

Technical Paper

9:50am - 10:20am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

Course

Fluid Simulation with the Lattice Boltzmann Method

3:45pm - 5:15pm PDT Sunday, 19 July 2026 Room 408 B

New Technologies

Production & Animation

Research & Education

Dynamics

Games

Simulation

Full Conference Supporter

Full Conference

DescriptionLattice Boltzmann Method (LBM) offers a powerful alternative to traditional Navier-Stokes solvers, using mesoscopic particle distributions on Cartesian lattices to achieve far superior GPU performance and accuracy. This 1.5h course introduces LBM fundamentals and recent advances in multiphase flows, free-surface flows, high–Reynolds-number flows, moving boundaries, and robotics. We also highlight applications of LBM in industrial simulation, game production, and visual effects.

People

Wei Li

Shanghai Artificial Intelligence Lab

Chaoyang Lyu

Mengyun Liu

Yixin Chen

INRIA / Ecole Polytechnique

Mathieu Desbrun

Kui Wu

LightSpeed Studios

Xiaopei Liu

Forget Superresolution, Sample Adaptively (when Path Tracing)

Technical Paper

9:50am - 10:00am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce an end-to-end adaptive sampling and denoising pipeline for sparse real-time path tracing. Our method trains stably despite discrete sampling decisions and uses perceptual, tonemapping-aware optimization to place samples where they matter most. It samples fine structures, specular highlights, shadows, producing more detailed reconstructions than superresolution or uniform sampling.

People

Martin Balint

Corentin Salaün

Hans-Peter Seidel

Karol Myszkowski

Forging the Glacier at IO Interactive: Fireside Chat with Henrik Schlichter (Technical Director)

Games Summit

2:30pm - 3:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionAs the game industry grapples with rising costs, shifting platforms, and an explosion of available tools, the question of how studios build their games has never been more consequential. IO Interactive Technical Director Henrik Schlichter sits down to discuss, debate, and unpack the realities of modern game development - what it takes to build the custom Glacier engine, innovate at scale, and how to build cheaper, faster and better without sacrificing quality. Equal parts technical deep-dive and industry reality check, this fireside chat sets the stage for bold conversations for Games at SIGGRAPH 2026.

People

Free-form Surface Approximation Using Rotational Patches

Technical Paper

2:20pm - 2:30pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a method to approximate free-form surfaces using rotational patches for architectural rationalization. By segmenting the input surface and optimizing B-spline-based patch layouts, followed by post-processing, we generate smooth, seamless quad meshes with locally repeated building elements (including beams, panels, and nodes), offering great potential for reducing fabrication costs.

People

University of Technology Sydney

Nico Pietroni

Yuanpeng Liu

RMIT University

Technical Paper

FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

9:30am - 9:40am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

DescriptionFreeOrbit4D is a training-free framework for camera redirection from monocular videos. By decoupling foreground and background reconstruction and completing foreground geometry via multi-view diffusion, it builds a foreground-complete 4D proxy that guides video generation, enabling faithful and temporally coherent novel views under large-angle camera trajectories.

People

Wei Cao

Hao Zhang

Fengrui Tian

Yulun Wu

Yingying Li

Shenlong Wang

FreeShell: A Context-Free 4D Printing Technique for Fabricating Complex 3D Triangle Mesh Shells

Technical Paper

3:55pm - 4:05pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionFreeShell introduces a robust thermal-shrinkage-actuated 4D printing technique for fabricating freeform thin-shell surfaces. By printing triangular tiles connected by shrinkable connectors using a single material, heating triggers the transformation from flat structures into 3D shells. An optimized mesh layout algorithm ensures geometric accuracy and robustness, reducing material and environment dependency.

People

Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University

Talks

From “Is It Real?” to “Is It Defensible?”: Governing AI-Assisted Media Production

4:45pm - 5:05pm PDT Tuesday, 21 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Ethics and Society

Generative AI

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

DescriptionProfessional GenAI production lacks auditable decision-making, failing legal scrutiny. Shifting from authenticity to "defensibility," Verifiable Story Production (VSP) operationalizes responsibility via Phase 0 (Human Intent) and four pillars: Sovereign Ingest, Constitutional Guardrails, Persistent Provenance, and Human Validation. VSP is an open standard now being evaluated in film school projects.

People

Nira Bozkurt

From Cloud to Set: Discussing the Future of Cloud, Adaptive, and AI-Native Production

Birds of a Feather

3:30pm - 4:30pm PDT Wednesday, 22 July 2026 Room 513

New Technologies

Production & Animation

Capture/Scanning

Digital Twins

Generative AI

Industry Insight

Pipeline Tools and Work

Real-Time

Rendering

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionCloud to Set: The Future of Adaptive and AI-Native Production is an exciting BOF session at SIGGRAPH featuring an award-winning panel of filmmakers, technologists, and creative innovators shaping the future of production. Panelists Erik Weaver (USC ETC), Erick Geisler (Global Objects, G2 Immersive Studios), and Christopher Nichols (Chaos Innovation Lab, Monstrous Moonshine) bring decades of combined experience across Emmy-winning work, groundbreaking VFX, and pioneering AI-native and cloud-based production pipelines. Designed as a BOF, the session emphasizes open dialogue, networking, and shared exploration, with dedicated Q&A and industry insights exchanged between panelists and attendees through discussion.

People

Eric Pinkel

CenterGrid

Virtual Studio

Art Paper

From Computer Vision to the Vision of Law: Human Overs[a]ight

3:00pm - 3:20pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Capture/Scanning

Computer Vision

Display

Ethics and Society

Generative AI

Hardware

Image Processing

Physical AI

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThe artwork HUMAN OVERS[A]IGHT: THE OPS ROOM is relevant to the SIGGRAPH community as it introduces the critical issues of lawmaking in the field of Artificial Intelligence. By bridging these disciplines, this translation aims to open a broader discourse on the topic from an innovative standpoint in media art that integrates legal matters, computer science, and a critical media theory approach.

People

Kristina Tica

Johannes Kepler University Linz

Joaquín Santuber

Johannes Kepler University Linz

Industry Session

From Game Engine to Production Engine

2:00pm - 2:50pm PDT Tuesday, 21 July 2026 Room 511C

Gaming & Interactive

New Technologies

Art

Games

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionFor many virtual production facilities, game engines became the foundation upon which modern LED volume workflows were built. Along the way, teams developed new disciplines, new processes, and new technical expertise to bridge the gap between real-time rendering and production requirements. This session shares StradaXR’s perspective on that journey and examines emerging approaches that seek to reduce workflow complexity, preserve creative intent, and bring production-ready content closer to the stage.

People

Ivan Reel

STRADA XR

Technical Workshop

From Human Vision to Machine Vision

9:00am - 12:15pm PDT Thursday, 23 July 2026 Room 406 AB

Research & Education

Art

Artificial Intelligence/Machine Learning

Augmented Reality

Computer Vision

Display

Image Processing

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionVisual computing encompasses the full range of technologies and methodologies involved in rendering, displaying, reconstructing, modeling, and recording visual data. Among the many subfields within visual computing, there has been a growing interest in two subfields in particular: human vision and machine vision. Human vision research focuses on understanding how human vision and cognition functions and using that knowledge to improve the user experience through realism, immersion, and responsiveness. In contrast, machine vision research focuses on building computational systems that complete a visual perception task, and may aim to mimic the structure or functionality of biological vision systems.

This workshop aims to facilitate dialogue and collaboration between researchers and practitioners in machine and human vision. By exploring common challenges, methodologies, and philosophical approaches, ranging from perceptually grounded models to data-driven deep learning frameworks, we hope to spark interdisciplinary discussion that drives innovation across the broader field of visual computing.

People

From Pixels to Physics: Building AI's Right Brain in the Open

Stage Session

1:00pm - 1:30pm PDT Tuesday, 21 July 2026 West Hall A

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Computer Vision

Generative AI

Graphics Systems Architecture

Physical AI

Real-Time

Rendering

Robotics

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionFoundational models aren't new, but building LTX taught us their scope is expanding faster and further than anyone predicted. LTX is our multimodal generative world model, and in this talk Ofir shows how a system trained to do one deceptively simple thing, generate pixels across time, a.k.a. video, becomes a physically grounded foundation that reasons about light, physics, and causality. If language models are the left brain of AI, LTX is a bet on the right: the intuitive, perceptual, physical side of intelligence.
We'll trace LTX's journey from a state-of-the-art open-weights model to core infrastructure across domains, from media and entertainment to physical AI. Expect real applications spanning robotics and simulation, a look under the hood at the architectural shifts that made it possible (MoE, stronger text encoders), and the conviction driving the project: when a model is open and production-ready, it compounds, for researchers, developers, enterprises, and the applications this room will build next.

People

Ofir Bibi

LTX

Talks

From Spark to Inferno: Scalable Stylized Fire in Disney and Pixar’s Hoppers

5:05pm - 5:25pm PDT Tuesday, 21 July 2026 Room 403 B

Production & Animation

Research & Education

Animation

Art

Capture/Scanning

Digital Twins

Dynamics

Industry Insight

Lighting

Pipeline Tools and Work

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionIn the film Hoppers, a forest fire rages and engulfs the glade which Mabel swore to protect. We describe how we crafted this fire through our production strategy, looks and rig development, fire ‘taxonomy’ and dressing, lighting and compositing workflows, and optimizations such as an optimized fire lighting representation.

People

Greg Gladstone

Max Gilbert

Linhan Li

Alexis Angelidis

Krzysztof Rost

Jon Reisch

FX Supervisor

From Splats to Worlds: Advanced 3DGS Applications

Birds of a Feather

8:30am - 10:00am PDT Tuesday, 21 July 2026 Room 518

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Capture/Scanning

Digital Twins

Generative AI

Geometry

Graphics Systems Architecture

Pipeline Tools and Work

Real-Time

Rendering

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

Description"Gaussian splatting has rapidly evolved from a novel radiance field reconstruction technique into a versatile foundation for real-time rendering, volumetric media, and spatial computing. This BoF session brings together researchers, engineers, and industry practitioners to explore the progression from 3D to 4D Gaussian representation.
Discussions will cover compression; animated Gaussian splatting; volumetric media from capture through distribution; 3DGS as a building block for world models bridging neural scene understanding with real-time engines; and the potential for 3DGS as a real-world archival format.
Come share progress, surface interoperability challenges, and help align where the ecosystem is heading.

People

Educator's Forum

From Studio Set to Render: A Collaborative Framework for Hybrid Media Education

11:25am - 11:45am PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Computer Vision

Digital Twins

Education

Games

Modeling

Pipeline Tools and Work

Rendering

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionAs the tools of photography and computer graphics become inseparable, the 'hybrid artist' is the new industry standard. This talk demonstrates how to bridge the lens-to-render gap by teaching students to navigate the collaborative methodologies of modern VFX and commercial production."

People

James Porto

Frontier Talk: Towards a Graphics-Silicon Gymnasium to Shape the Future of Micro-Embodied AI

Frontiers

8:00am - 8:45am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Hardware

Physical AI

Full Conference Supporter

Full Conference

Experience

DescriptionThe graphics community thrives on standardized APIs and accessible GPU silicon. However, a parallel frontier awaits in micro-embodied AI, where tiny units capture images, perform mental geometric simulations, and intelligently act under constraints. However, the traditional graphics research abstraction breaks down in this regime. GPUs do not fit, and diverse custom silicon lacks common APIs. Confined to simulation, graphics researchers cannot access physical experimentation to explore their native challenges. This talk envisions a graphics-silicon gymnasium to bridge the gap and unlock fundamental questions: What new graphics algorithms emerge under the unique constraints of tiny, specialized silicon? What minimum properties are required for mental geometric simulations at miniature scales? We walk through semiconductor history to confirm absolute physical constraints, explore an illustrative camera-equipped smart ingestible pill, and discuss the merits of a gymnasium environment that can empower the graphics community to shape the future of micro-embodied AI.

People

Christopher Torng

Frontier Talk: UNIX V4 and the Utah Teapot

Frontiers

8:00am - 8:45am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Education

Full Conference Supporter

Full Conference

Experience

DescriptionWe recently recovered UNIX V4 from a 1974 magnetic tape at the University of Utah. This version of the UNIX operating system, thought to have been lost, was the 19th copy distributed to the public, just months after the first public announcement. It was originally acquired by Martin Newell while managing the computer graphics laboratory, and it was likely connected to his foundational research in procedural modeling and the famous Utah teapot. This talk shows the unique insight this artifact provides into the dawn of computer graphics and the history of UNIX.

People

Thalia Archibald

Frontier Talk: Write Once, Read ALWAYS: Reading Computer Graphics through Critical Code Studies

Frontiers

8:00am - 8:45am PDT Monday, 20 July 2026 Room 408 B

Arts & Design

Research & Education

Art

Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionMost programmers don't want people looking too closely at their code, except the parts where they found that clever hack or ingenious workaround. And now with AI some people don't even read the code they generate. But what if we looked closer at code? This talk introduces Critical Code Studies, a field that uses computer source code as an entrypoint for discussing culture, philosophy, and the way we see and represent the world. Focusing on examples from the world of computer graphics, I will explore what your code may say about you and about the world you are modeling and envisioning.

People

Mark Marino

Frontier Workshops: Digital Twins for Science and Industry

Frontiers

9:00am - 12:15pm PDT Sunday, 19 July 2026 Room 501 ABC

New Technologies

Digital Twins

Physical AI

Robotics

Scientific Visualization

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis workshop addresses the transformative role of digital twins across science and industry. Following the National Academies' 2024 standardized definition, we seek to foster a community of practice embracing this common understanding across diverse domains. We open with a 2026 state-of-the-art survey and Digital Twin Consortium perspectives on evolving standards, then examine societal impacts in healthcare, fusion energy, climate science, and sovereign AI. Technical sessions address rendering fidelity in virtual replicas, AI integration for prediction and optimization, and frameworks combining machine learning with physics-based simulation. Case studies span drug discovery, computational biomedicine, sustainable energy, entertainment production, and scientific visualization.

People

Immersionary Enterprises, LLC

Andrea Townsend-Nicholson

Dan Isaacs

Digital Twin Consortium

Jeff Adie

Oak Ridge National Laboratory

Nicholas Polys

Virginia Tech University

Scott Greenwood

Frontiers

Frontiers Workshop: CTRL-G: Controllable Generative Graphics for Games

2:00pm - 5:15pm PDT Monday, 20 July 2026 Room 501 ABC

Gaming & Interactive

New Technologies

Artificial Intelligence/Machine Learning

Games

Generative AI

Graphics Systems Architecture

Performance

Physical AI

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionThe CTRL-G (Controllable Generative Graphics for Games) workshop explores the critical intersection of generative AI and interactive game development. While generative models are transforming content creation, the central challenge for games remains control: steering these models in real time to align with player intent, production pipelines, and artistic requirements.

This three-hour session brings together AI researchers, graphics/VFX professionals, and ethicists to address two core themes: developing controllable world models—such as adaptive, player-responsive environments—and evolving game engine education to incorporate these new hybrid workflows. By bridging technical innovation with production realities and ethical considerations, CTRL-G aims to define a practical agenda for integrating generative AI into modern game engines. Participants will gain actionable insights into state-of-the-art techniques, integration challenges, and the pedagogical shifts necessary to prepare the next generation of developers for an AI-augmented industry.

People

Frontiers Workshop: Dronevision, Holodecks, and Spatial Computing Using Swarms of Flying Light Specks

Frontiers

9:00am - 12:15pm PDT Thursday, 23 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Digital Twins

Display

Geometry

Graphics Systems Architecture

Haptics

Hardware

Networking

Performance

Physical AI

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThis timely SIGGRAPH 2026 Frontiers workshop explores Flying Light Specks (FLSs), including their applications, current capabilities, and future research directions. An FLS is a miniature drone equipped with a lighting apparatus that serves as a building block for next-generation display systems. These systems range from desktop Dronevision platforms to room-scale holodecks and outdoor spatial-computing environments. Swarms of FLSs can illuminate graphics and animations visible to the naked eye, enabling users to interact with them using their bare hands. Topics include the classification of FLS devices with LightBender as a representative example, end-to-end architectures spanning content generation, illumination, and bare-hand interaction.

For more information visit: https://www.flsworkshop.com

People

Shahram Ghandeharizadeh

Shahram Ghandeharizadeh

Frontiers Workshop: Form and Function: A Hands-On Workshop on Computationally Designing and Fabricating Barrier-Grid Animations

Hamed Alimohammadzadeh

Frontiers

2:00pm - 5:15pm PDT Thursday, 23 July 2026 Room 501 ABC

Arts & Design

New Technologies

Research & Education

Animation

Art

Display

Fabrication

Image Processing

Full Conference Supporter

Full Conference

Experience

DescriptionThis frontiers workshop equips participants with hands-on experience using a modern computational design workflow for creating and fabricating barrier-grid animations. Participants will author animations whose occlusion patterns are shaped by mathematical functions, preview them under multiple interaction modes, and fabricate take-home artifacts. By participating in this workshop, attendees will understand how to design expressive barrier-grid animations that balance form and function.

People

Ticha Sethapakdi

Maxine Perroni-Scharf

Ticha Sethapakdi

Frontiers Workshop: Graphics In Medicine: From the Dev Floor to the Operating Room 2

Frontiers

2:00pm - 5:15pm PDT Sunday, 19 July 2026 Room 501 ABC

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Industry Insight

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe're back for round 2 of "From the Dev Floor to the Operating Room"! Like last year, we hope to bring to light more of the wonderful applications of computer graphics in medicine. We'll be discussing current challenges with XR in medicine, digital twins, simulation, robotics and more.
We'll also expand on last years workshop activity with a brand new panel of physicians to help us practice designing graphics solutions for medicine that actually make an impact.

This will also be a great place to network with people interested the beautiful intersection of Medicine and Technology

People

Enoch Omale

Enoch Omale

James Hu

Cook Children's Medical Center

Jacob Alford

Sina Soltanzadeh Zarandi

Cleveland Clinic Foundation

Brian Lien

Kotaro Tsutsumi

Anthony Le

Cedars-Sinai Medical Center

Kevin Seals

Frontiers

Frontiers Workshop: Quantum Machine Learning: Bridging Quantum Computing & Machine Learning

9:00am - 12:15pm PDT Monday, 20 July 2026 Room 501 ABC

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

Experience

DescriptionQuantum Machine Learning (QML) is emerging as a transformative field connecting quantum computing with modern machine learning and AI. This workshop explores how quantum-based approaches can support new learning paradigms, hybrid quantum–classical architectures, generative models, and computer graphics pipelines. Emphasizing both theory and practice, the workshop will examine near-term quantum hardware, deployable system design, and rigorous evaluation methods for identifying meaningful quantum advantage. Through three keynote talks, a panel discussion, open dialogue, and roadmap synthesis, the workshop aims to foster interdisciplinary collaboration and help shape the future of scalable, practical, and impactful QML.

People

Wei Zhang

Augusta University

Tianming Liu

The University of Georgia

Yingfeng Wang

University of Tennessee at Chattanooga

Xiang Li

Harvard Medical School

James Hendler

Rensselaer Polytechnic Institute

Thilanka Munasinghe

Rensselaer Polytechnic Institute

Jennifer Wei

National Aeronautics and Space Administration

Birds of a Feather

Fulbright Program International Exchange Opportunities

1:00pm - 1:30pm PDT Wednesday, 22 July 2026 Room 510

Research & Education

Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionAre you interested in international exchange? Come be inspired and informed as a Fulbright alumnus describes his personal experience. Find out how you can develop a strong application for this prestigious academic and professional exchange program, now celebrating its 80th year. The Fulbright Program is the flagship international exchange program sponsored by the United States Government. In partnership with more than 160 countries worldwide, Fulbright offers an expansive suite of life-changing international academic and cultural exchange opportunities. Learn more at https://fulbrightprogram.org/apply/

People

David Thornton

Jacksonville State University

Fulbright Program

Technical Paper

Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering

3:55pm - 4:05pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Games

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe propose using Gabor kernels as volumetric density primitives to enable compact, cheap and continuous level-of-detail to primitive-based physically-based volume rendering with single and multiple scattering. We show state-of-the-art results in regression quality, runtime performance and introduce novel stochastic techniques for trading quality and performance in volume rendering.

People

Jorge Condor

Nicolai Hermann

Mehmet Ata Yurtsever

Piotr Didyk

Game Audio Lasagna: Building Layers to Create New Sonic Worlds

Games Summit

10:45am - 11:15am PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Audio

Games

Full Conference Supporter

Full Conference

Experience

DescriptionJoin a Composer and Sound Designer as they share a glimpse into how they build sonic palettes and craft unique audio experiences for games. Hear examples of how various layers of different sounds can create a fireball spell, which unique combination of instruments create an unsettling atmosphere, or even how to evoke a specific emotion within just a few seconds of audio.

In addition to diving into the details on how these sound effects and musical excerpts were made, we’ll also focus on the high level decisions that would inform the audio’s direction. Analyzing how to determine that which is most important for audio to represent, aligning across multiple teams on creative goals, and other essential considerations for the production of audio for games.

People

Sword and Sound Audio

Real-Time Live!

Game-Ready Hair in Minutes! Hair Mesh Modeling with Physics

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe show how game-ready hair models can be prepared within minutes using our new Hair Mesh modeling framework that combines mesh modeling operations with physics simulation. The resulting Hair Mesh models can be used for generating individual hair strands with a variety of styles for high-quality real-time hair rendering/simulation.

People

Cem Yuksel

Cyber Radiance

Mayar Youksell

Salt Lake Center for Science Education

Technical Paper

Garment Particles: A 2D–3D Symmetric Garment Representation for Generation and Editing

2:20pm - 2:30pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionGarment Particles is a 5D point-cloud representation that jointly encodes 2D sewing patterns and 3D geometry. This representation enables Garment Particles Flow (GPF) and Particles-to-Pattern Flow (PPF), a rectified flow framework for both simulation-ready sewing pattern generation from text and images and intuitive 2D/3D editing via diffusion posterior sampling.

People

Kiyohiro Nakayama

I-Chao Shen

Ruofan Liu

Garments - Interactive Discussion

Technical Paper

3:00pm - 3:30pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse Smoke Reconstruction

9:00am - 9:10am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a physics-aware method for reconstructing dynamic fluids from sparse-view videos. By integrating volumetric rendering with physically guided Gaussian optimization, it enforces consistency in density and motion, reducing artifacts and improving realism. The approach achieves accurate, stable 3D smoke reconstruction with high visual and physical fidelity.

People

State Key Lab for Novel Software Technology, Nanjing University

Technical Paper

Gaussian Point Splatting

2:20pm - 2:30pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose Gaussian point splatting, a stochastic method for rendering massive 3DGS scenes. By sampling pixel-sized opaque points, splatting them atomically, and applying stochastic transparency, we eliminate the need for sorting. Our approach distributes workload evenly across GPU threads, enabling the real-time display of hundreds of millions of Gaussians efficiently.

People

Joris Rijsdijk

Christoph Peters

Michael Weinmann

Ricardo Marroquim

Gaussian Reconstruction - Interactive Discussion

Technical Paper

4:35pm - 5:05pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

Birds of a Feather

Gaussian Splatting for Animation: Emerging Workflows and Hybrid Pipelines

10:00am - 11:30am PDT Wednesday, 22 July 2026 Room 510

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Augmented Reality

Capture/Scanning

Digital Twins

Image Processing

Industry Insight

Pipeline Tools and Work

Real-Time

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionGaussian Splatting is emerging as a high-fidelity, real-time alternative to traditional 3D representations, with growing relevance for captured environments, performances, and animation workflows.
This Birds of a Feather session invites technical directors, animators, researchers, and tool developers to discuss how Gaussian-based representations can integrate into production pipelines, from acquisition and layout to lighting, editing, and delivery.
Topics include hybrid mesh/splat workflows, animated representations, interoperability, volumetric capture, and stop-motion digitization. The session will emphasize shared challenges, emerging practices, and open exchange across studios, academia, and tool developers.

People

Eloi Champagne

National Film Board of Canada

Computer Animation Festival

Gauze

12:30pm - 1:30pm PDT Wednesday, 22 July 2026 411 Theatre

Full Conference Supporter

Full Conference

Description14-year-old Zain, a Palestinian swimming champion, faces war and man-made famine. He becomes the sole caregiver to his little brother. When aid drops into the sea, desperate for food, Zain is forced to swim—not for passion, but for survival.

People

Director

Director

Director

Director

Director

Technical Paper

gCDT: A Highly Parallel GPU Algorithm for Large-Scale Constrained Delaunay Triangulation

2:00pm - 2:10pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a highly parallel GPU algorithm for 2D constrained Delaunay triangulation that robustly handles arbitrary valid constraints. It computes triangulations of up to 10 million vertices in 0.1 seconds on an RTX 4090, substantially outperforming prior GPU methods and widely used CPU implementations across diverse benchmark inputs.

People

Ruofeng Tong

Lili He

Peng Du

Shenzhen Poisson Software Co., Ltd.

Hailong Li

Technical Paper

Generalized Aberrations for Processing-Aware Optical Design

4:35pm - 4:45pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Fabrication

Haptics

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionOptimal imaging performance requires designing optics with the downstream processing in the loop—especially as AI pipelines grow in importance. Yet the scalar nature of loss functions in the processing-aware setting breaks industry-standard lens design solvers. We generalize classical ray aberrations to task-driven objectives, bringing robust solvers to end-to-end design.

People

Geoffroi Côté

Keysight Technologies

Keysight Technologies, Princeton University

Technical Paper

Generalized Spherical Harmonics Products using Spherical Grids

4:25pm - 4:35pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Games

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe introduce the Generalized Spherical Harmonics Product, a novel method supporting inputs with different SH orders and flexible output truncation. Using Spherical Grids as an intermediate representation, we reduce SH products to simple point-wise multiplications, achieving 3.5–6.5× speedup over state-of-the-art methods while maintaining accuracy for real-time rendering applications.

People

Mohamed bin Zayed University of Artificial Intelligence

Kun Xu

Generative 3D & Editing - Interactive Discussion

Technical Paper

11:55am - 12:25pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

Technical Paper

Generative 3D (2) - Interactive Discussion

10:00am - 10:25am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

Technical Paper

Generative 3D Gaussians with Learned Density Control

9:50am - 10:00am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

DescriptionDeG is an image-to-3D generative framework for Gaussian splatting that learns to place detail adaptively. It evaluates each Gaussian’s effect on rendering loss, then reinforces density in important regions and suppresses less useful ones, enabling variable-resolution, high-quality 3D asset generation.

People

Runjie Yan

Institute for Interdisciplinary Information Sciences, Tsinghua University

Technical Workshop

Generative AI Meets Computer Graphics

2:00pm - 5:15pm PDT Wednesday, 22 July 2026 Room 406 AB

Research & Education

Generative AI

Full Conference Supporter

Full Conference

DescriptionGenerative AI is rapidly becoming a unifying interface for computer graphics, connecting large language models (LLMs), visual language models (VLMs), and video foundation models with geometry- and physics-aware representations. Led by experts from the University of Pennsylvania, MIT CSAIL, University of Utah, and UCLA, this workshop explores how modern generative models are reshaping the classical graphics pipeline, spanning 3D content creation, physics simulation, and animation. The program features a distinguished lineup of confirmed speakers from Stanford, the University of Chicago, Anuttacon, and Meshy AI, representing both academic pioneers and industry leaders.

The primary objective is to address the fundamental challenges of deploying generative methods in real-world production, specifically focusing on the controllability and editability of generated content, physical plausibility and consistency over time, and practical integration into professional workflows for film, games, and CAD. Attendees can expect a highly interactive session structure that moves beyond theory into practical application. The workshop includes five 30-minute invited talks and two 15-minute lightning talks highlighting emerging directions like garment synthesis and character animation. Most importantly, the session concludes with an 85-minute moderated panel and open audience discussion designed to synthesize themes, identify actionable open problems, and foster direct engagement between researchers and practitioners.

People

Lingjie Liu

Minghao Guo

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Rana Hanocka

University of Chicago

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Yao Feng

Generative Modeling with Orbit-Space Particle Flow Matching

Technical Paper

2:50pm - 3:00pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionOrbit-Space Geometric Probability Paths (OGPP) is a flow-matching framework for generative modeling of particle systems that exploits shared geometric structure and uses probability path geometry to encode geometric information. It enables high-quality, efficient generation of particle configurations and point-cloud surfaces with normals, achieving state-of-the-art performance across diverse generation tasks.

People

Sinan Wang

Jinjin He

Shenyifan Lu

Ruicheng Wang

Greg Turk

Bo Zhu

Generic Variational Spacetime Optimization of Vortex Core Manifolds

Technical Paper

9:40am - 9:50am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a highly efficient variational framework for computing optimal vortex cores in 3D unsteady flows. By unifying diverse detection criteria through time-preintegrated Lagrangians, our method accurately reconstructs spacetime vortex manifolds by solving Euler-Lagrange equations in just one time step, enabling rapid and robust flow analysis.

People

Xingdi Zhang

King Abdullah University of Science and Technology (KAUST)

Peter Rautek

King Abdullah University of Science and Technology (KAUST)

Markus Hadwiger

King Abdullah University of Science and Technology (KAUST)

Technical Paper

GenPIE: A Time-Resolved Plenoptic Imager

2:40pm - 2:50pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

DescriptionWe present a physically grounded generative imaging system to resolve high-dimensional, time-resolved plenoptic light transport from sparse measurements. Using decoupled laser-detector capture, 3D foundation-model priors, and differentiable transient rendering, we reveals indirect light transport for applications including multi-bounce separation, time unwarping, and time-resolved relighting.

People

Ziheng Wang

The Chinese University of Hong Kong, Shenzhen

Siyuan Shen

Huanyu Xu

Kaichun Qiao

Longwen Zhang

Qixuan Zhang

The Chinese University of Hong Kong, Shenzhen

Qilin Sun

Point Spread Technology

Shiying Li

Geometry Processing - Interactive Discussion

Technical Paper

11:55am - 12:20pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

Technical Paper

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

3:45pm - 3:55pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionGeoQuery is a geometry-guided single-step diffusion framework for mitigating query contamination in existing multi-view self attention mechanism. By retrieving proxy features from clean reference views via geometric correspondences, it bypasses corrupted query features and enables high-fidelity restoration for sparse-view 3D Gaussian Splatting.

People

Xiao Cao

University of Electronic Science and Technology of China

University of Electronic Science and Technology of China

Lixin Duan

University of Electronic Science and Technology of China

Birds of a Feather

Geospatial and 3D Tiles

9:00am - 10:00am PDT Thursday, 23 July 2026 Room 518

New Technologies

Research & Education

Graphics Systems Architecture

Pipeline Tools and Work

Scientific Visualization

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionIn this session we'll cover how glTF is being used for runtime-efficient streaming of 3D geospatial data and digital twins. This includes a wide range of content types like Gaussian splats, point clouds, vector data, volumetric data, and AEC/CAD/BIM. We'll also look at glTF 2.1's new complex scenes capabilities and how this scales to massive datasets.

People

Art Paper

Gesture Flux: Unveiling Budaixi Hand Gestures through Mixed Reality Performance

10:45am - 11:05am PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Digital Twins

Display

Dynamics

Education

Ethics and Society

Games

Geometry

Hardware

Lighting

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis work presents Gesture Flux, an immersive performance system integrating mixed-reality gesture recognition, Budaixi (traditional Taiwanese glove puppetry), and contemporary dance. Through three interaction modes, hidden puppeteering gestures are transformed from direct articulation to perceptual extension and energetic radiation, visualized as dynamic traces and extended into full-body performance, proposing a cross-disciplinary approach to cultural reinterpretation and embodied interaction.

People

Yi Jen Lin

National Chiao Tung University

Wei-Chen Yen

National Chiao Tung University

Chun-Cheng Hsu

National Chiao Tung University

Birds of a Feather

GFXReconstruct - an Engine for Vulkan Debugging and Profiling

2:00pm - 3:00pm PDT Monday, 20 July 2026 Room 518

Gaming & Interactive

New Technologies

Research & Education

Graphics Systems Architecture

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionGFXReconstruct is an open-source framework for capturing, replaying, and analyzing Vulkan applications. This BOF will explore how developers can use GFXReconstruct as the foundation for debugging, profiling, and performance analysis workflows, both from the command line and through integrated tools. Attendees will learn about recent project updates, use cases, and opportunities to contribute feedback and help guide future development.

People

Brad Grantham

LunarG

Technical Paper

GimmBO: Interactive Generative Image Model Merging via Bayesian Optimization

9:30am - 9:40am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionGimmBO helps users interactively explore combinations of customized image generation styles to create desired results. It replaces manual slider tuning with a tailored Preferential Bayesian Optimization approach, outperforming alternatives in simulations and user studies. It further extends to combining content and scaling to large model collections by integrating model retrieval.

People

Chenxi Liu

Selena Ling

Alec Jacobson

Vector Institute

Birds of a Feather

Global CG Pipelines

3:00pm - 4:30pm PDT Tuesday, 21 July 2026 JW Marriott - Plaza 1

Gaming & Interactive

New Technologies

Production & Animation

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionA casual discussion on production pipeline development. Come talk shop about the latest trends, common concerns, and best practices.

This is part of a linked series of Technical Pipeline BoFs, covering the Reference Platform, Renderfarming, Cloud, Pipeline, and Storage. Attendees will receive invites to our 'Beers of a Feather' event, the same evening.

People

Ryan Bottriell

Global Discrete Optimization for Quad-Dominant Mesh Reduction

Fran Zandonella Benjamin

The Pipeline Conference

Technical Paper

9:20am - 9:30am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe propose a global optimization framework for simplifying quad-dominant meshes used in game and animation production. By formulating edge selection as an Integer Linear Programming problem with partial poly-chord segmentation and curvature-aware constraints, our method preserves clean edge flows and quad topology far better than existing greedy approaches.

People

Yuzhe Luo

Sate Key Lab of CAD&CG, Zhejiang University

LIGHTSPEED, China

Jingchen Gao

Institution Jason Moore Productions / The MetaMovie

Technical Paper

GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization

4:15pm - 4:25pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionGMT is a Geometric Multigrid Transformer that significantly accelerates microstructure homogenization. Embedding Transformers into the multigrid hierarchy to capture multi-scale physical interactions delivers a 160x speedup over SOTA GPU solvers while maintaining engineering-grade accuracy at high resolutions. GMT enables real-time material screening, multi-scale simulations, and rapid inverse design of metamaterials.

People

Yu Xing

Tianyang Xue

Lin Lu

Go-with-the-Track: Video Compositing and Motion Control with Point Tracking

Technical Paper

9:10am - 9:20am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

DescriptionWe present Go-with-the-Track, a video generation framework conditioned on multiple reference images and point-tracks that jointly anchor the generated frames and the references. Our approach enables precise control over motion and multi-reference compositing, unlocking a wide range of applications, including video restylization, keypoint- and mesh-driven compositing, and camera motion control.

People

University of California, Los Angeles

Ryan Burgert

Eyeline Labs

Stony Brook University

Birds of a Feather

11:00am - 12:00pm PDT Tuesday, 21 July 2026 JW Marriott - Plaza 1

Production & Animation

Animation

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionJoin a participant-driven discussion with key representatives from the graphics community, comparing experiences and exploring techniques related to pushing the production pipeline and resources toward cloud native architecture and deployment.

This is part of a linked series of Technical Pipeline BoFs, covering the Reference Platform, Renderfarming, Cloud, Pipeline, and Storage. Attendees will receive invites to our 'Beers of a Feather' event, the same evening.

People

Immersive Pavilion

Goo Goo Clash: A Co-located Mixed Reality VE-Sport Experience

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionGoo Goo Clash is a high-energy "VE-Sport" that reimagines the classic "Snake" arcade game for Mixed Reality. Multiple players physically sprint within a shared arena using standalone headsets. By blending real-world athleticism with digital strategy, it transforms isolating VR into a thrilling, scalable, and co-located competitive spectator sport.

People

Pinyo Tanradtanamonthon

Art Paper

Gorgon Loop: An Interactive Art Installation Revealing Algorithmic Judgment through Machine Vision and Generative Language

2:40pm - 3:00pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Capture/Scanning

Computer Vision

Display

Ethics and Society

Generative AI

Hardware

Image Processing

Physical AI

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionGorgon Loop makes algorithmic judgement in public space visible as a collective, embodied process. Through machine vision, language models, and group commentary, it exposes how limited data, bias, and automation shape social evaluation, offering a critical lens on the cultural consequences of AI perception.

People

Shuang Li

伦敦大学金史密斯学院

Patrick Hartono

RMIT University Vietnam

Technical Paper

GPC: Large-Scale Generative Pretraining for Transferable Motor Control

2:00pm - 2:10pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present Generative Pretrained Controllers, a framework for training reusable generative controllers for physically simulated characters. GPC leverages FSQ discretization with end-to-end RL to learn reusable motor skills from large-scale motion data. Once trained, the generative controller can be finetuned and adapted to perform diverse downstream tasks using naturalistic behaviors.

People

Yi Shi

GPU Ray Tracing using NVIDIA OptiX and OWL

Course

9:00am - 12:15pm PDT Wednesday, 22 July 2026 411 Theatre

New Technologies

Rendering

Full Conference Supporter

Full Conference

DescriptionThis course teaches attendees how to use GPU Ray Tracing through NVIDIA’s OptiX API and the NVIDIA OptiX Wrappers Library (OWL). Attendees taking this course should be able to write their own GPU ray tracers, even without having to become experts in PTX/IR embedding or Shader Binding Tables.

People

University of Cologne

Technical Paper

GPU-accelerated Certified Hausdorff Distance Between Triangle Meshes

2:20pm - 2:30pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a GPU-accelerated certified algorithm for the directed Hausdorff distance between triangle meshes. By replacing recursive branch-and-bound with a parallel wavefront pipeline, it delivers millisecond-scale, tolerance-controlled results on models with millions of triangles, enabling interactive geometric queries while closely matching state-of-the-art CPU accuracy on large, challenging benchmark datasets.

People

Universidade Federal de Santa Catarina

Leonardo Sacht

Qiang Zou

GR3EN: Generative Relighting for 3D Environments

Technical Paper

2:10pm - 2:20pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionGR3EN enables relighting 3D environments to user-specified lighting conditions. It provides full control over every light source in a 3D scene — enabling adding new light sources, changing the color of existing ones or turning them off entirely. Shadows, reflections, and interreflections all update realistically.

People

Xiaoyan Xing

University of Amsterdam

Art Gallery

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionGradi is a suite of speculative wearable intrafaces that exposes the seams in AI’s promise of effortless interaction. Each device examines a dominant logic shaping AI culture: calibration, compression, prediction, and mediation. Calibration holds you in permanent beta. Compression lets a proxy speak through your body. Prediction keeps you within the guardrails of the sayable. Mediation polishes speech into identityless fluency. Through interactive subversive artifacts and videos of strange use cases, Gradi challenges tacit expectations with quiet perversion, trading frictionless and phantasmagoric integration for situated misalignments. A permanent rehearsal that keeps the seam visible and felt.

People

Technical Paper

Gradient Descent in the ALPS: Abstracted Low-Poly Stylization and Fabrication

9:50am - 10:00am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe generate 2D low-poly meshes that abstract images using score distillation sampling. We focus on ensuring the validity of the output mesh, quantized palette colors and semantic similarity to the input. The resulting vector images are easy to edit and fabricated as mosaics, embroidery, crocheting, patchwork and stencils.

People

Technical Paper

Gradient Domain Reconstruction for Monte Carlo PDE Solvers

3:55pm - 4:05pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a gradient-domain Monte Carlo framework for solving Poisson equations on complex domains. The method directly estimates solution differences between query points and reconstructs the final solution efficiently, reducing variance and improving convergence without introducing additional bias beyond the underlying WoS-based solver.

People

Jiaqi Wu

Xuejun Hu

Kun Xu

Gradient-based Design of Non-Uniform Low-Discrepancy Samples

Technical Paper

11:25am - 11:35am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionThis paper introduces a first numerical optimization method for approximately generating non-uniform low-discrepancy point sets with an arbitrary target distribution. It is based on a new differentiable estimator of non-uniform L2-discrepancy for a given point set.

People

Xiangyu Li

Ege Ciklabakkal

University of Waterloo

Daniel Ritchie

Graphical X Splatting (GraphiXS): A Graphical Model for 4D Gaussian Splatting under Uncertainty

Toshiya Hachisuka

University of Waterloo

Technical Paper

2:00pm - 2:10pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionGraphical X Splatting (GraphiXS) is a novel probabilistic framework for systematically modelling data uncertainty in 4D Gaussian Splatting. It handles various types of spatial and temporal sparsity, including missing frames and sparse viewpoints, and generalizes across diverse primitives. Extensive evaluations show that GraphiXS outperforms existing methods across a range of sparse data scenarios.

People

Doga Yilmaz

Jialin Zhu

Baidu Research

Deshan Gong

He Wang

Graphics4Science 2026: Graphics for Cross-Scale Reliable Scientific Instruments

University of Leeds

Technical Workshop

9:00am - 12:15pm PDT Monday, 20 July 2026 Room 406 AB

New Technologies

Research & Education

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Education

Fabrication

Generative AI

Geometry

Image Processing

Math Foundations and Theory

Modeling

Physical AI

Rendering

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

DescriptionComputer graphics is increasingly central to modern scientific discovery, providing not only visualization but also physically grounded modeling, simulation, inverse problem formulations, and interactive systems for hypothesis generation. Building on the Graphics4Science course at SIGGRAPH 2025, Graphics4Science 2026 adopts a workshop-style format with fewer broadcast talks, deeper technical presentations, and more discussion. The program features four keynotes spanning computational imaging, scientific reconstruction for structural biology, generative modeling for molecular structures, and reduced-order modeling for physical simulation, complemented by two curated lightning-talk sessions highlighting advances from the community.

As graphics-based methods move from retrospective analysis toward guiding experiments and engineering decisions, a shared requirement across these areas is reliability. In this workshop, reliable scientific instruments refers to methods and systems that remain useful under scientific constraints, including limited or noisy measurements, distribution shift across instruments and conditions, and the need to communicate uncertainty.

This notion of reliability includes physical and geometric validity, numerical stability under perturbations, calibrated uncertainty estimates, and clearly stated assumptions and failure modes. It also includes practical concerns such as reproducible pipelines, transparent reporting, and interfaces that allow scientists to interrogate and stress-test results rather than treating models as black boxes.

Against this backdrop, Graphics4Science 2026 aims to move beyond a catalog of applications toward an actionable technical agenda for graphics-enabled science. A unifying theme of the workshop is translation: connecting computational methods to scientific constraints, evaluating progress when ground truth is limited, and packaging techniques into practical tools that domain experts can trust, use, and iterate on.

People

Minghao Guo

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Mina Konaković Lukovic

Qixing Huang

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Peter Yichen Chen

King Abdullah University of Science and Technology (KAUST)

Wolfgang Heidrich

Emerging Technologies

Ground Spin Strike: Presentation of Impact Sensations by a Floor-Mounted Turntable

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis study proposes a floor-mounted turntable that enhances impact sensation in VR by simulating reaction forces to the feet during striking actions. Unlike conventional hand-based haptic devices, the proposed approach leverages whole-body force propagation. We demonstrate a VR-based sports application that enhances impact realism through instantaneous rotational feedback.

People

Mutsuki Shimada

The University of Electro-Communications

Izumi Mizoguchi

The University of Electro-Communications

Hiroyuki Kajimoto

The University of Electro-Communications

Technical Paper

Guidestar-Free Adaptive Optics with Asymmetric Apertures

2:00pm - 2:10pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

DescriptionWe introduce and demonstrate the first closed-loop adaptive optics system capable of optically correcting aberrations in real-time without a guidestar or a wavefront sensor. We enable these capabilities by combining asymmetric apertures, machine learning–based PSF estimation and phase retrieval algorithms, and a high resolution spatial light modulator.

People

Christopher A. Metzler

University of Maryland, College Park

Technical Paper

Hair, Fur & Feathers - Interactive Discussion

9:50am - 10:20am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

Technical Paper

HairGPT: A Unified Autoregressive Framework for 3D Realistic Hairstyle Synthesis

9:00am - 9:10am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionHairGPT introduces a paradigm shift toward strand-as-language modeling, reformulating 3D realistic hair generation as a dual-decoupled autoregressive process where strands are treated as the fundamental generative units.

People

Haimin Luo

min Ouyang

Deemos Technology Co., Ltd.

HairLRM: Strand-based Hair Modeling via Large Reconstruction Models

Technical Paper

9:10am - 9:20am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionHairLRM integrates Large Reconstruction Model (LRM) geometric priors into strand generation. Leveraging an LRM mesh anchor and a Dual Orientation AutoEncoder, it transforms coarse geometry into high-fidelity strands, disentangling complex topologies to set a new benchmark for robust, accurate hair reconstruction.

People

Yuefan Shen

State Key Laboratory of CAD & CG, Zhejiang University

Yican Dong

Xiufeng Huang

Hong Kong Baptist University

Zhongtian Zheng

State Key Laboratory of CAD & CG, Zhejiang University

Youyi Zheng

Kui Wu

HairPort: In-context 3D-aware Hair Import and Transfer for Images

Technical Paper

9:20am - 9:30am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionHairPort is a 3D-aware hairstyle transfer method that faithfully moves a reference hairstyle onto a source face image, even under large pose and scale differences. By separating hair removal from synthesis and enforcing geometric consistency through 3D reconstruction, HairPort achieves accurate, identity-preserving results that outperform existing approaches.

People

Alireza Heidari

Amirhossein Alimohammadi

Wallace Michel Pinto Lira

Hands-on Course: Sponsored by Autodesk: From Footage to Previs: AI Mocap Workflows with Autodesk Flow Studio and Maya

Course

3:30pm - 5:00pm PDT Wednesday, 22 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionThis hands-on course is designed for professional animation and VFX artists with experience using Autodesk Maya who want to explore new approaches to previsualization and early production.

Using Autodesk Flow Studio, participants will work with live-action footage to generate editable exports such as AI mocap, camera tracking, character passes, clean plates, full 3D scenes, and more. These elements will be used as a foundation for exploring performance, camera movement, and spatial storytelling before heavy asset development begins. The workshop focuses on how early creative exploration can inform layout, shot design, and production planning.

Through practical examples and guided walkthroughs, participants will understand how Flow Studio can support early iteration and integrate with Maya to establish creative intent and a production-ready foundation.

Learning Objectives
By the end of the hands-on course, participants will be able to:
· Use Flow Studio to generate editable mocap data, camera tracking, character passes, clean plates and full 3D scenes from live-action footage
· Apply Flow Studio outputs to previsualization and layout workflows in Maya
· Explore performance, camera movement, and scene layout during early production
· Export and refine AI-generated elements using USD and FBX
· Identify opportunities to incorporate Flow Studio into early-stage animation and VFX pipelines

Target Audience
Animation and VFX artists, technical directors, and Maya users working in visual effects, animation, and games, as well as students with Maya experience.

Experience Level
intermediate (prior experience with Maya and VFX pipelines recommended.)

People

Duane Rutkowski

Hands-on Course: Accelerate Robot Learning With NVIDIA Isaac Lab and Newton

Course

10:00am - 11:30am PDT Wednesday, 22 July 2026 Concourse Hall

New Technologies

Artificial Intelligence/Machine Learning

Digital Twins

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionHands-on course on Newton, a GPU-accelerated physics engine, and its integration with Isaac Lab for robot learning. Covers Newton’s architecture and import pipeline, solver and contact tuning, articulation and sensors, then training and evaluating policies in Isaac Lab with Newton as the physics backend.

People

Course

Hands-on Course: Advance World Simulation With 3D Gaussian Splatting for Large-Scale Environment Reconstruction

12:00pm - 1:30pm PDT Thursday, 23 July 2026 Concourse Hall

New Technologies

Research & Education

Capture/Scanning

Computer Vision

Digital Twins

Physical AI

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionLearn how to reconstruct a large scene for robotics testing using NVIDIA Omniverse NuRec Gaussian-based reconstruction technologies to perform multi-GPU training, object segmentation, and extraction. This lab will walk through core concepts with a step-by-step workflow for data capture, reconstruction, and object level-integration for robotics simulation in NVIDIA Isaac Lab.

People

Zoë LaLena

Hands-on Course: Debugging USD composition

Course

1:45pm - 3:15pm PDT Wednesday, 22 July 2026 Concourse Hall

Gaming & Interactive

Production & Animation

Animation

Games

Performance

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionThis hands-on course focuses on debugging USD composition in production. Participants gain practical experience authoring data across composition arcs and diagnosing issues in complex scenes. Building on USD in Production, the course emphasizes interactive use of modern debugging and visualization tools to understand how opinions, overrides, and data resolve.

People

Pallav Sharma

Nick Porcino

Joan Panis

Hands-on Course: Dreaming in 4 dimensions: generating media with Gemini, Genie, and Veo

Course

1:45pm - 3:15pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Education

Generative AI

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionMove beyond static pixels into explorable, playable worlds, generative images, and generative video. Join Google DeepMind engineers as we get hands-on, using NanoBanana Pro for reasoned concept art, Veo 3.1 for video generation, and Genie 3 to turn images and text into playable, interactive worlds.

People

Paige Bailey

DeepMind

Google

Course

Hands-on Course: Hands-on Programming and Running Quantum Teleportation

2:45pm - 4:15pm PDT Tuesday, 21 July 2026 Concourse Hall

New Technologies

Artificial Intelligence/Machine Learning

Computer Vision

Education

Image Processing

Math Foundations and Theory

Performance

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionIn this hands-on programming course you'll learn how to write and run quantum computing code. Then you'll program the quantum teleportation algorithm, and run it on a high-quality simulator to transfer the state of a quantum bit to your partner, who will decode it to get your secret message.

People

Andrew Glassner

Consultant

Course

Hands-on Course: NVIDIA: From 3D Captures to Simulated Digital Environments

10:15am - 11:45am PDT Thursday, 23 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Physical AI

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionWe introduce a novel capture-to-simulation pipeline for in-the-wild 3D Gaussian Splat scenes,
showing our research-based solutions for segmenting objects, predicting their volumetric mechanical properties using a recent learning-based method, and mixed splat-mesh physics simulations, all supported by recent features in the Kaolin Library.

People

Course

Hands-on Course: NVIDIA: Hands-On Machine Learning with Slang: Building High-Performance GPU Inference Pipelines

12:00pm - 1:30pm PDT Tuesday, 21 July 2026 Concourse Hall

New Technologies

Artificial Intelligence/Machine Learning

Computer Vision

Generative AI

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionLearn to build GPU ML inference pipelines with Slang. Use a lightweight, open set of pre-written kernels to implement an MNIST CNN from scratch: load SafeTensors weights, run inference, and apply kernel fusion for better performance. Hands-on, cross-platform, and highly customizable—ideal for games, tools, and research.

People

Christopher Hebert

Hands-on Course: NVIDIA: Introduction to Slang: The Next-Generation Shading Language

Course

10:15am - 11:45am PDT Tuesday, 21 July 2026 Concourse Hall

Gaming & Interactive

New Technologies

Artificial Intelligence/Machine Learning

Games

Graphics Systems Architecture

Performance

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionThis hands-on course introduces Slang, an open-source, open governance shading language hosted by Khronos that simplifies graphics development across platforms. Designed to tackle the growing complexity of shader code, Slang offers modern programming constructs while maintaining top performance on current GPUs.

People

Course

Hands-on Course: NVIDIA: Simulating a Dextrous Hand For Robotics With OpenUSD

11:45am - 1:15pm PDT Wednesday, 22 July 2026 Concourse Hall

New Technologies

Research & Education

Digital Twins

Physical AI

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionHands-on course on preparing robot USD assets for simulation, covering why physics tuning is foundational to robot learning, inspecting and configuring colliders and joints with OpenUSD/PhysX, and tuning control gains for stable, realistic motion. Participants work with a robot hand asset and apply best practices for simulation-ready authoring.

People

Course

Hands-on Course: Powered By Gaussian Splats: From World Models to 3D Interactive Worlds

3:30pm - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionFrom the SensAI Hackademy team behind Splat Analyzer and the World Model end-to-end workflow kits, this hands-on workshop shows the complete pipeline of working with AI-generated world models and reconstructed Gaussian splat scenes, turning them into fully interactive and playable web experiences using 3D object detection, segmentation, and browser-native workflows

People

Nigel Joe Al Hartman

SensAI Hackademy

Alex Coulombe

HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads

Technical Paper

11:15am - 11:25am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionHeadRouter is a training-free image editing framework tailored for Multimodal Diffusion Transformers (MM-DiTs). It addresses diminishing text guidance by adaptively routing attention heads based on semantic sensitivity and refining token representations. The method improves semantic alignment and structural preservation over state-of-the-art baselines through dynamic head-level control without additional training mechanisms.

People

Yu Xu

Institute of Computing Technology Chinese Academy of Sciences

Fan Tang

Juan Cao

Institute of Computing Technology Chinese Academy of Sciences

Xiaoyu Kong

Beihang University

Yuxin Zhang

Institute of Computing Technology Chinese Academy of Sciences

Jintao Li

Oliver Deussen

University of Konstanz

Tong-Yee Lee

National Cheng Kung University

Yu Xu

Heart Mountain Wyoming Foundation

Computer Animation Festival

Hello Maggie!

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

Descriptionn 2007, former World War II Heart Mountain Incarceration Camp incarceree Shig Yabu and former Topaz Incarceration Camp incarceree Willie Ito published the children's picture book, Hello Maggie! Yabu wrote the autobiographical story about how he was forced to give away his pets when he was removed from his home in San Francisco, and how he eventually adopted a baby magpie in Wyoming. The bird, which he named Maggie, became Yabu’s constant companion during his time in camp, and eventually learned to mimic human speech. Ito, a veteran artist and animator at Disney, Warner Brothers, and Hanna-Barbera, illustrated the story.

In 2025 the Heart Mountain Wyoming Foundation produced a 23 minute animated version of the classic children's book.

People

Logan Christie

Producer

Tony Tarantini

Director

Sheridan College

Willie Ito

Producer

Heart Mountain Wyoming Foundation

Carlo Chiarotti

Composer

Nemo Academy

Technical Paper

Heterogeneous Subspace Corrections for GPU Deformable Multibody Dynamics

10:55am - 11:05am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionHeterogeneous Subspace Corrections (HSC) accelerates GPU simulations of complex multibody systems. By decoupling deformable and rigid/affine components into separate Neumann-preconditioned Krylov iterations and utilizing an Adaptive Cross Approximation (ACA) for low-rank coupling, it overcomes ill-conditioning to achieve direct-solver convergence speeds for stiff, high-resolution models.

People

Hi-SPAD: Video-Rate Hyperspectral Imaging and Inference with Single-Photon Cameras

Technical Paper

11:45am - 11:55am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionThis work develops a hyperspectral imager using a SPAD image sensor that achieves a spatial resolution of 1024 × 768 pixels across 123 spectral bands spanning visible and near-infrared wavelengths, at a temporal rate of 26 frames per second.

People

Haejoon Lee

Mohit Gupta

Vijayakumar Bhagavatula

Aswin Sankaranarayanan

Haejoon Lee

Higgsfield AI | Kök Börü: An Artist-First Approach to AI in Animation

Stage Session

3:00pm - 3:30pm PDT Wednesday, 22 July 2026 West Hall A

Arts & Design

New Technologies

Production & Animation

Animation

Art

Diversity, Equity and Inclusion

Generative AI

Networking

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionKök Börü is a hybrid hand-drawn and AI-integrated animated short that tells a rare Central Asian story, the kind the traditional greenlight system tends to overlook. In this session, the team behind the film gives you the full picture in brief, covering why this story needed to exist, a condensed look at the hybrid pipeline that made it possible, and the real budget, team, and timeline numbers behind it. At its heart, though, this is just an honest conversation about AI and animation. We will look at where these tools genuinely help, where they fall short, and how they can open doors for underrepresented voices without pushing the artist out of the center of the work.

People

Amina Ömirjan

Higgsfield AI

Technical Paper

High-Fidelity 4D Cloth Capture Pipeline with a Two-Level Pattern

2:40pm - 2:50pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a 4D (spatio-temporal) cloth capture system and a two-level pattern that achieves 1mm spatial resolution using only 16 RGB cameras. Our method produces temporally coherent sequences with no self penetration that faithfully capture fine wrinkles and folds even during complex motions with self-contact.

People

Technical Paper

High-Order Continuous Geometrical Validity

9:20am - 9:30am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Geometry

Hardware

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a conservative algorithm to test the geometrical validity of polynomial finite elements as they deform linearly in time. In elastodynamic simulation, our algorithm guarantees that the system remains physically valid during the entire trajectory, not only at discrete time steps, even when implemented using floating point arithmetic.

People

Real-Time Live!

HiPR: Hierarchical Progressive Rendering for Immediate Feedback

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionRe-rendering an entire frame after every scene modification — especially small changes — is wasteful. Our Hierarchical Progressive Rendering (HiPR) method only re-renders modified objects and their light transport dependencies. It enables interactively-rendered edits by directing samples where light and change actually matter.

People

ACM SIGGRAPH 365

History: Fueling the Future by Preserving the Past - The ACM SIGGRAPH History Archive

1:00pm - 2:00pm PDT Thursday, 23 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionIf you are interested in the history of computer graphics, this session is for you. The ACM SIGGRAPH History Archive is both a physical collection and an online archive of SIGGRAPH organization leadership and events, conference presentations, demonstrations, animation screenings, art exhibitions, and more. The archive is a volunteer effort involving pioneers, professionals, students, and community members. This session will showcase the new additions to the archive and include short talks by student interns and volunteers. We will also focus on how this incredibly information-rich archive has fueled the future of computer graphics research and creative endeavors.

The archive has grown tremendously and now includes more than 75,000 pages of information. One of the most significant contributions to the community is opening up the archive so the AI bots could learn from 52 years worth of conference presentations, demonstrations, animation screening, etc. Today, Gemini, ChatGPT and other AI assistants often cite the ACM SIGGRAPH History Archive and the information related to the history of computer graphics is much more accurate. Another significant addition was the programming of an online inventory system that tracks the 4000+ physical artifacts in the collection. Eighteen years worth of SIGGRAPH Asia conference content was also added to the archive along with the unique programs from SIGGRAPH's past such as performances, competitions, and special sessions and events. Overall, this session is an exciting way to capture a glimpse into SIGGRAPH's past and speculate on how access to this information will alter computer graphics' future trajectory.

People

ACM SIGGRAPH History Committee

Chair

ACM SIGGRAPH History Committee

Chair

Janice Searleman

Adjunct Research Professor

Clarkson University

Kai Yabis

Camille Leber

Jenna Mauch

Aliyah Wise

Lillian Aulls

HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

Technical Paper

2:30pm - 2:40pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce HL-OutPaint, a coarse-to-fine framework for high-resolution long-range video outpainting. HL-OutPaint incorporates a novel global-local frame swapping mechanism that enables both long-term and short-term temporal consistency. Experimental results show that our approach produces spatially and temporally coherent results across diverse real-world high-resolution long-range videos.

People

Visual Display Business, Samsung Electronics

Kyuha Choi

Visual Display Business, Samsung Electronics

Youngseok Han

Visual Display Business, Samsung Electronics

Sunghyun Cho

POSTECH

Technical Paper

Holography & Displays - Interactive Discussion

11:55am - 12:25pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

Technical Paper

HoloPathTracer: Fast and Accurate Wave Path Tracing for Holography

11:15am - 11:25am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionTo bring physically accurate 3D cues to holography, HoloPathTracer moves beyond prior computer-generated holography pipelines that separate radiance rendering from wave propagation. By tracing complex wave paths directly through the scene, it enables phase-only holograms with natural defocus, reflections, refractions, and more faithful visual realism.

People

Wenbin Zhou

Xiangyu Meng

Jiankai Xing

Xin Liu

Suyeon Choi

How To Build End-To-End Physical AI Systems for Robots

Course

3:45pm - 5:15pm PDT Sunday, 19 July 2026 Room 408 A

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Hardware

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionThis course covers building end-to-end physical AI for humanoid and general robots. Covers data generation with NVIDIA Cosmos (Predict, Transfer) and synthetic data; training with Isaac Lab (RL/imitation) and GR00T VLAs; and deployment on the edge with Jetson Thor. Instructors: Edith Llontop, Akul Santhosh.

People

ACM SIGGRAPH 365

How to Get Your Resume & Reel Noticed

9:00am - 10:00am PDT Thursday, 23 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Animation

Art

Education

Games

Lighting

Modeling

Performance

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionThe ACM SIGGRAPH Early Career Development Committee’s “Resume and Reel Review” program has long offered students and early career professionals the chance to have their work reviewed by industry experts at SIGGRAPH conferences.

This session will feature a panel of industry professionals who will discuss and review a selection from this year’s program live. This unique opportunity allows attendees to see real-time reviews, learn what makes a great resume and reel, and ask questions directly to experts.

Register for a one-on-one session at https://ecdc.siggraph.org.

People

Senior Recruiter

CFX Artist

Gracie Arenas Strittmatter

Supervising Director of Tiburon Technical Operations

Electronic Arts

AJ Christensen

Senior Visualization Designer

NASA Scientific Visualization Studio

Craig Slagel

ACM SIGGRAPH Early Career Development Committee

RunGo

Course

How to write a Vulkan application in 2026

9:00am - 12:15pm PDT Wednesday, 22 July 2026 Petree D

Gaming & Interactive

Education

Games

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis Khronos course covers major Vulkan improvements since version 1.0, focusing on extensions such as descriptor heaps and dynamic rendering that improve developer productivity. It introduces key Vulkan concepts and provides comprehensive guidance for writing and modernizing Vulkan applications in 2026, focusing on resource, pipeline, draw, and synchronization management.

People

Jose Emilio Muñoz Lopez

Arm

Technical Workshop

Human–AI Co-Creation in Generative Art: Graphics Methods, Systems, and Applications

9:00am - 12:15pm PDT Tuesday, 21 July 2026 Room 406 AB

Arts & Design

Research & Education

Art

Artificial Intelligence/Machine Learning

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionRecent advances in generative AI are transforming how visual and spatial content is created, enabling new forms of collaboration between humans and intelligent systems. This workshop explores human–AI co-creation in generative art, where AI acts not merely as an automation tool but as a creative partner supporting exploration, iteration, and artistic expression. The workshop brings together researchers, artists, and engineers from computer graphics, machine learning, human–computer interaction, and computational design to examine emerging systems for collaborative creativity. Topics include interactive creative tools, generative models for visual and 3D art, and fabrication-aware design systems that connect digital creation with real-world production. The workshop will feature keynote talks and interactive discussions exploring questions such as artistic control in generative systems, effective interfaces for co-creation, and integrating fabrication constraints into generative design, aiming to inspire new directions for human–AI collaboration in generative art and design. More details in: https://human-ai-cocreation.github.io/

People

Ying Jiang

Jiayin Lu

Yunuo Chen

Yael Vinker

The Hong Kong University of Science and Technology (Guangzhou)

Zeyu Wang

Jennifer Jacobs

Maneesh Agrawala

HumanFlow: Controllable Human Image Generation via Flow Matching

Technical Paper

9:40am - 9:50am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionHumanFlow is a unified flow-matching framework for controllable full-body human image generation. It introduces a Control Encoder, Token-ControlNet, and topology-aware loss for structural consistency, along with the large-scale MiCoGen dataset, achieving improved controllability and fidelity over existing diffusion and flow-based methods.

People

Wuhan Textile University

Hong Ding

Guangxi University of Finance and Economic

Chunxia Xiao

Humans & Hands - Reconstruction - Interactive Discussion

Technical Paper

4:45pm - 5:15pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

Technical Paper

Hybrid Gaussian Wang Tiles for Class-aware Authoring and Rendering

2:00pm - 2:10pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a multi-class Gaussian Splatting Wang Tiles framework for synthesizing large, detailed scenes from multiple exemplars. Our method enables smooth transitions via hybrid tile mixing, supports real-time rendering with hybrid CPU–GPU sorting, and provides an interactive authoring tool for editing class distributions and scene structure.

People

Yunfan Zeng

Li Ma

Eyeline

Pedro V. Sander

Course

Hydra in Production

9:00am - 12:15pm PDT Tuesday, 21 July 2026 Room 515 A

Production & Animation

Animation

Industry Insight

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionBased on real production examples, Hydra in Production will present best practices and case studies of how to integrate OpenUSD's Hydra library into a content creation tool or pipeline, and leverage it to solve complex pipeline challenges and enable powerful workflows. This is a companion course to USD in Production.

People

Thomas Cauchois

Joe Longson

Anna Reid

Brett Levin

HydraOps: Replacing an In-House Lighting and Rendering Runtime with Hydra 2.0

Talks

3:45pm - 4:05pm PDT Thursday, 23 July 2026 Room 408 A

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Graphics Systems Architecture

Image Processing

Lighting

Performance

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionHydraOps is the first production, artist-facing lighting framework built on Hydra 2.0 within OpenDCC, unifying interactive and final rendering from a single USD scene. Replacing a legacy in-house engine with Hydra’s modular scene index architecture, it streamlines evaluation, reduces complexity, and lowers maintenance costs.

People

Talks

Igniting Performance in Avatar: Fire and Ash - a Case Study in Varang's Facial Performance

4:25pm - 5:05pm PDT Wednesday, 22 July 2026 Room 515 A

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Performance

Full Conference Supporter

Full Conference

DescriptionThis talk explores how Wētā FX’s Anatomically Plausible Facial System enabled Varang’s ferocious, emotionally authentic performance in Avatar: Fire and Ash. Using Neytiri as a case study, we examine the motivations behind a revolutionary shift in facial technology and end-to-end development challenges required for Varang to stand alongside legacy characters.

People

Technical Paper

Image Editing - Interactive Discussion

11:45am - 12:15pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

Technical Paper

Image Generation - Interactive Discussion

10:00am - 10:30am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

Technical Paper

Imaging, Video, and HDR - Interactive Discussion

3:00pm - 3:30pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

Technical Paper

Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion

11:35am - 11:45am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionImg2CADSeq is a multi-stage pipeline converting single-view images into parametrically editable 3D CAD models. Using a coarse-to-fine hierarchical codebook and VQ-Diffusion , it bridges 2D visual features with 3D semantics , generating standard STEP files ready for direct commercial software use.

People

Shiyu Tan

Zixuan Zhao

Hao Gao

Zhiheng Chen

Xiaolong Yin

Enya Shen

Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency

Haihe Lab of ITAI

Technical Paper

4:05pm - 4:15pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose a 3D Gaussian Splatting reconstruction method with immediate feedback that handles unordered image captures and very large scenes. Through fast place-recognition-driven matching, cluster-based loop closure with graph-propagated correction, and a progressive Gaussian hierarchy construction, it achieves robust, scalable reconstruction at a fraction of offline processing times.

People

Andreas Meuleman

Inria, Université de Rennes

Linus Franke

Inria, Université Côte d'Azur

Boris Zhestiankin

Inria, Université Côte d'Azur

EPFL

Camille Montemagni

Inria, Université de Rennes

George Drettakis

Inria Université Côte d'Azur

Immersive Pavilion

Immersive Virtual Reality Training for Laboratory Mouse Blood Collection

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis VR-based instructional program trains learners in mouse cheek blood collection under the 3Rs principles. It bridges classroom instruction and laboratory practice by allowing novices to rehearse procedures safely in a virtual environment, while the simulation familiarizes them with settings prior to on-site training, enhancing readiness and reducing animal distress.

People

Yi-Jie Lu

Digital Learning Center, National Taiwan University

Wan-Jung Wang

Digital Learning Center, National Taiwan University

I-Hsuan Lin

Digital Learning Center, National Taiwan University

Hsin-Sun Huang

Animal Resource Center, National Taiwan University

Chia-Pin Yu

School of Forestry & Resource Conservation, National Taiwan University

Digital Learning Center, National Taiwan University

Hui-Wen Chen

Department of Veterinary Medicine, National Taiwan University

Animal Resource Center, National Taiwan University

Birds of a Feather

Immersive Visualisation for Science, Research, Art and Digital Twins Applications

8:00am - 9:30am PDT Monday, 20 July 2026 Room 513

Arts & Design

New Technologies

Research & Education

Augmented Reality

Digital Twins

Display

Graphics Systems Architecture

Physical AI

Real-Time

Scientific Visualization

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionTraditionally (and since 2014), this session is about immersive visualization systems, software, and tools for science, research, scientific visualization, information visualization, art, design and digital twins. Invited speakers and panelists discuss newest initiatives and developments in immersive space as applied to data exploration, scientific discoveries, and more.

Detailed agenda can be found under https://vis-bof.matters.today

People

Technical Paper

Implicit Minimal Surfaces for Bijective Correspondences

3:45pm - 3:55pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe introduce an implicit representation of continuous, bijective, orientation-preserving maps between genus zero surfaces with or without boundary. The distortion of these maps can easily be minimized by optimizing the Ginzburg-Landau functional---a ubiquitous model in physics and differential geometry---leading to a simple algorithm for computing bijective correspondences using only standard tools of the tangent vector field toolbox. The method avoids combinatorial mesh modifications and does not require barrier functions to enforce bijectivity making it more robust to noise and simpler to implement.

People

Etienne Corman

CNRS, Inria, LORIA

Yousuf Soliman

Side Effects Software Inc

Robin Magnet

INRIA

Université Paris Cité

Mark Gillespie

INRIA

Implicit Surface Compression -- with Good Old Discrete Cosine Transform and Motion Compensation

Technical Paper

2:00pm - 2:10pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a real-time 4D compression framework for volumetric capture using the Truncated Signed Distance Field (TSDF) as coding domain. Combining DCT-based spatial coding with motion-compensated temporal prediction, our training-free GPU-accelerated system enables real-time encoding and decoding while substantially reducing bitrate for dynamic 3D content.

People

Tao Jin

Shengxi Wu

Tianshu Huang

Mallesham Dasari

Srinivasan Seshan

Anthony Rowe

Impulse: Dawn of the Digital Dance Studio

Bosch Research

Immersive Pavilion

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis immersive installation invites attendees to directly engage with Impulse, an artist-made Unreal Engine tool for real-time choreography. Through hands-on motion capture and mixed reality visualization, participants can record movement, apply it across multiple digital dancers, and experiment with spatial composition in real time.

People

Computer Animation Festival

In Conversation with Brad Bird

10:45am - 11:45am PDT Tuesday, 21 July 2026 Hall K

Full Conference Supporter

Full Conference

DescriptionJoin two-time Academy Award-winning filmmaker Brad Bird (“The Incredibles,” “Ratatouille”, “The Iron Giant”) for an exclusive SIGGRAPH conversation about “RAY GUNN,” his highly anticipated animated detective, neo-noir coming to Netflix.

Set in Metropia—a dazzling retro-futuristic metropolis imagined as the future through the lens of 1939—RAY GUNN follows Raymond Gunn, the last human private detective, as he becomes entangled in a mystery involving aliens, murder, and a celebrity whose fame may conceal dangerous secrets. Described by Bird as “”The Maltese Falcon” meets “Buck Rogers,”” the film blends classic detective storytelling with expansive science-fiction world-building.

For decades, Bird has pushed the boundaries of what animation can achieve, creating richly realized worlds that are as emotionally engaging as they are visually groundbreaking. With “RAY GUNN,” he brings that signature style to an ambitious new universe, combining noir atmosphere, Art Deco-inspired design, and cutting-edge animation to create a world unlike anything seen on screen before.
Featuring never-before-seen insights into “RAY GUNN”'s development and production, this session offers a rare opportunity to hear one of animation’s most influential storytellers discuss the art, technology, and creative vision behind his latest cinematic achievement.

People

Director

VFX Supervisor

Animation Director

Computer Animation Festival

In Conversation with Tyree Dillihay

2:00pm - 3:30pm PDT Sunday, 19 July 2026 Petree D

Full Conference Supporter

Full Conference

DescriptionMaking his feature directorial debut with Sony Pictures Animation, Tyree Dillihay joins us to look back on the making of "GOAT," the story of a small goat with big dreams who gets a once-in-a-lifetime shot to join the pros and play roarball, a high-intensity, co-ed, full-contact sport dominated by the fastest, fiercest animals in the world.

Blending a unique, original visual style with the kinetic energy of modern basketball culture, the film is a love letter to the underdog spirit. In this conversation, Dillihay will discuss bringing his vision to life with an A-list voice cast led by Caleb McLaughlin and Gabrielle Union, working with producer Stephen Curry and other NBA legends including Andre Iguodala to achieve authentic roarball action, and what it took to make his feature debut at one of animation's most celebrated studios.

People

Garth Burkhard

Senior Vice President of Publicity & Digita

Sony Pictures Animation

Tyree Dillihay

Director

Sony Pictures Animation

Desirae Witte

In Defense of Euler Angles in Game Programming

Talks

3:00pm - 3:20pm PDT Sunday, 19 July 2026 Room 403 B

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Education

Games

Generative AI

Image Processing

Simulation

Full Conference Supporter

Full Conference

DescriptionWhen teaching 3D rotations, the prevailing rationale is to avoid Euler angles due to gimbal lock. In many game situations, quaternion slerp produces undesirable effects while Euler angle interpolation actually results in the correct behavior. Students should learn to select rotation representations that produce appropriate motion for the application.

People

Matthew Whiting

in-between: home, belonging, and the Asian diaspora

Art Gallery

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Description“in-between" is a modular installation about the immigrant experience and the difficulty of defining home. Born in Philippines and raised across China, Japan, and United States, I translate my own migration history—and seven interviews with Asian diaspora who moved to Tokyo—into fragile material and participatory data portraiture. The work unfolds in three parts: “deportation”, a two-hour performance where water drips onto washi printed with my life-journey at a cadence driven by worldwide searches for “deportation”; “home:1–8”, silkscreened interview portraits mounted in space; and “home:collective”, where visitors add their journeys and are paired with a stranger whose definition of home resonates.

People

Shirley Wu

studio hua

Art Paper

Infant Vision: Reconfiguring Perception in Mixed Reality

9:00am - 9:20am PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Research & Education

Animation

Art

Audio

Augmented Reality

Capture/Scanning

Dynamics

Hardware

Lighting

Performance

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis work interweaves vision science with perceptual experience in art. Leveraging MR technology, it renders the infant's mysterious vision into a first-person experiential artwork. For the SIGGRAPH community, the project serves as a case study of how scientific theories and domain knowledge can be transformed into an embodied, explorable experience. Through exhibition, we found that Infant Vision opens other senses and encourages participants to reimagine the world.

People

Wei Chen Yen

national yang ming chiao tung university

Seth Riskin

national yang ming chiao tung university

Chun-Cheng Hsu

Technical Paper

InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation

9:40am - 9:50am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce InfiniteDiffusion, a training-free algorithm enabling diffusion models to generate spatially infinite outputs with the core properties of procedural noise: seed-consistency (determinism) and constant-time random access. We incorporate a novel architecture for terrain generation to produce Terrain Diffusion, a learned, real-time, infinite terrain generator with a procedural noise-like interface.

People

Alexander Goslin

Inside DAC: Creative Connections Across SIGGRAPH’s Digital Arts Community

ACM SIGGRAPH 365

11:45am - 12:45pm PDT Monday, 20 July 2026 Room 404 AB

Arts & Design

Research & Education

Art

Education

Full Conference Supporter

Full Conference

Experience

DescriptionLooking for ways to connect with SIGGRAPH’s creative side? This session offers an open and inviting introduction to the ACM SIGGRAPH Digital Arts Community (DAC), a vibrant network that brings together artists, designers, technologists, and researchers working across digital and computational media arts.

Attendees will get a clear overview of how DAC supports creative exchange through inclusive programs designed to encourage experimentation, dialogue, and collaboration across disciplines. The session highlights key DAC initiatives, including SPARKS Lightning Talks, online and hybrid exhibitions, and the student digital art competition, along with opportunities for global engagement through partnerships with organizations such as ISEA and Expanded Animation.

Whether you are a student, a first-time SIGGRAPH attendee, or someone curious about engaging more deeply with SIGGRAPH’s creative communities, this session provides a friendly entry point into DAC’s activities and a chance to discover how you can share your work, connect with others, and participate in an international network of digital arts practitioners.

People

Chair

Jan Searleman

Adjunct Research Professor

Clarkson University

Gustavo Rincon

Sanglim Han

Assistant Professor

Chung-Ang University

Wei He

Chewing Theory Studio

University of Applied Sciences Upper Austria

Peijing Mou

UCLA Design Media Arts

Juergen Hagler

Expanded Animation

Joyce Pei

Pratt Institute

Spatial Storytelling

Inside the Show: A Live VR Performance and the Backstage Systems Behind It

10:15am - 11:00am PDT Tuesday, 21 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Education

Performance

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionA live Spatial Storytelling performance that pairs a short VR scene with a real-time “backstage reveal.” One performer acts in VR while a company member projects the live experience onto the screen, then demonstrates the hidden tools that drive the show, including triggers, actor menus, and control systems.

People

Virtual Worlds Company

Christopher Lane Davis

Ferryman Collective

Whitton Frank

The Ferryman Collective

Technical Paper

Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration

9:30am - 9:40am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionInspiration Seeds is a generative framework that combines two input images into diverse, visually coherent compositions—without text prompts. Trained on synthetic triplets using CLIP Sparse Autoencoders, it uncovers latent visual relationships between inputs, supporting early-stage creative exploration where designers seek emergent ideas from loosely connected visual references.

People

Integrating Neural Graphics into Vulkan Rendering Pipelines on Arm: A Fireside Conversation with the Teams Behind Neural Dawn - Arm x Sumo

Stage Session

3:00pm - 3:30pm PDT Tuesday, 21 July 2026 West Hall A

Gaming & Interactive

New Technologies

Production & Animation

Artificial Intelligence/Machine Learning

Games

Graphics Systems Architecture

Hardware

Industry Insight

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

Description"Neural graphics techniques have moved into production rendering workflows in games and this is becoming true in mobile. This fireside-style session brings together engineers and developers from Arm and Sumo Digital to discuss the development of Neural Dawn, a production-quality Unreal Engine 5 mobile title built using Arm Neural Technology.

The discussion focuses on the practical realities of integrating neural graphics into Vulkan rendering pipelines for mobile hardware. Topics include workload scheduling, frame graph integration, memory bandwidth constraints, debugging, performance validation, scalability across device classes, and balancing visual quality against demanding performance targets.

Panelists will also examine how Arm Vulkan extensions and neural technologies influenced rendering and engine decisions during development, alongside broader ecosystem considerations such as portability, tooling, and preparing for emerging neural graphics hardware capabilities.

Drawing on perspectives from engine developers, artists, and production teams, the session provides a grounded view of what it takes to move neural graphics from prototype to shipping content. Attendees will leave with practical insight into the technical tradeoffs and rendering architecture decisions involved in building real-world neural graphics workflows on Arm platforms."

People

Talks

Interactive Rigging of Art-directed and Stylized Plants

11:45am - 12:05pm PDT Monday, 20 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Dynamics

Games

Generative AI

Geometry

Modeling

Performance

Pipeline Tools and Work

Real-Time

Simulation

Full Conference Supporter

Full Conference

DescriptionPlants in recent films at DreamWorks Animation are complex and stylized and may not conform to hierarchical and physical structures. From just input models of plants, our environment rigging toolset can produce rigs procedurally and interactively allowing the artist to control the process and account for the stylization and complexity.

People

Arunachalam Somasundaram

DreamWorks Animation

Technical Paper

Interactive Yarn-level Knitwear with Nested Douglas-Rachford Splitting

11:35am - 11:45am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a novel framework utilizing a generalized Douglas-Rachford Splitting (DRS) scheme and hierarchical decomposition for high-resolution knitwear simulation. By convexifying complex yarn dynamics, it ensures robust, optimal convergence. With matrix-free GPU parallelization, our method achieves interactive simulation rates for multi-million DOF garments.

People

Technical Paper

Inverse Rendering - Interactive Discussion

10:00am - 10:30am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

Technical Paper

Inverse Rendering for Discrete X-Ray Computed Tomography

9:00am - 9:10am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose a gradient-based discrete tomography method that models each voxel as a probability distribution over known materials, minimizing an object-space loss for projection consistency. Inspired by inverse rendering, it outperforms classical methods, supports scattering, and excels in sparse and limited-angle scenarios.

People

Lovro Nuic

Ziyi Zhang

Korbinian Sager

Carl Zeiss AG

Wenzel Jakob

Invisible Holographic Window: Full-color 3D Image Reconstruction from Transparent Surface-relief Computer-generated Holograms

Technical Paper

10:45am - 10:55am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe demonstrate an invisible holographic window: a transparent surface‑relief computer-generated hologram formed on glass. Using a scattering‑suppressed encoding scheme and spatial‑frequency band‑division multiplexing, we achieve high‑transmittance, crosstalk‑free full‑color 3D image reconstruction, allowing clear viewing of a photorealistic holographic image overlaid in front of real‑world scenes through the glass.

People

Ryo Higashida

Masato Miura

Teruyoshi Nobukawa

Yuta Yamaguchi

Ken-ichi Aoshima

Nobuhiko Funabashi

Masahiro Yamaguchi

InvSculpt: Inverse Sculpting Modeling via Controlled 3D Generation and a Vector Displacement Field

Technical Paper

11:15am - 11:25am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe propose InvSculpt, which decomposes a mesh into a base shape and reusable details represented by a vector displacement field. It uses text-guided 2D priors and a 3D flow model for mask-free detail removal while preserving identity. The method enables accurate decomposition and high-fidelity detail transfer.

People

Hengyu Meng

The Hong Kong University of Science and Technology (Guangzhou)

The Hong Kong University of Science and Technology (Guangzhou)

Lanjiong Li

The Hong Kong University of Science and Technology (Guangzhou)

Zhijing Shao

Yingda Yin

Lingting Zhu

Zeyu Hu

Xin Wang

The Hong Kong University of Science and Technology (Guangzhou)

Laoshan Laboratory

Zeyu Wang

Iris3D: 3D Generation via Synchronized Diffusion Distillation

Technical Paper

10:45am - 10:55am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionIris3D is a novel 3D generation system that combines feedforward reconstruction models with a new Synchronized Diffusion Distillation (SDD) method to produce detailed geometry and vivid textures. By addressing view inconsistency and over-smoothing issues in traditional Score Distillation Sampling (SDS) methods, it enables controllable and high-quality 3D content creation.

People

Yixun Liang

Weiyu Li

Rui Chen

Fei-Peng Tian

Light Illusions

Jiarui Liu

Ying-Cong Chen

Ping Tan

Xiao-Xiao Long

Yixun Liang

Iskra: A System for Inverse Geometry Processing

Technical Paper

2:00pm - 2:10pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionIskra is a system for differentiating through solutions to geometry processing problems.
It differentiates a broad class of algorithms, exploiting existing fast problem-specific schemes common to geometry processing, including local-global and ADMM solvers. It is compatible with machine learning frameworks, opening doors to new classes of inverse geometry processing applications.

People

Ahmed Mahmoud

IsoGami: Rigid-Deployable Kirigami Materials From Isohedral Tilings

Technical Paper

4:45pm - 4:55pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a computational method to design rigid-deployable Kirigami sheets based on isohedral tilings. By exploring combined topology and geometry spaces, our approach identifies self-deployable structures with controlled expansion. Our approach generates diverse designs, demonstrated through an interactive browser and validated with 3D-printed prototypes.

People

Bernhard Thomaszewski

It’s Not Just a Phase: Creating Phase-Aligned Peripheral Metamers

Technical Paper

4:45pm - 4:55pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present a method for enhancing the perceived quality of foveated images by extrapolating local image statistics, such as intensity, orientation and especially phase, from coarse to fine scales. In particular, we demonstrate that correct phase alignment across space and scales is crucial for achieving perceptually convincing image quality.

People

Sophie Kergaßner

Piotr Didyk

JGS2-GQ: Training-free 2nd Jacobi with Gaussian Quadrature

Technical Paper

4:35pm - 4:45pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionJGS2-GQ replaces data-driven Cubature with training-free Gaussian Quadrature, enabling stable, high-resolution GPU simulation. It handles frictional contact, maintains Newton-like convergence, and outperforms JGS2 by 50% on novel deformations without training.

People

Lei Lan

Weiwei Xu

Just-Dub-It: Video dubbing via Joint Audio-Visual Diffusion

Technical Paper

4:25pm - 4:35pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Games

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionJUST-DUB-IT is a unified audio-video diffusion model for automatic video dubbing. It jointly synthesizes translated speech and synchronized lip movements via a lightweight LoRA adapter, replacing traditional pipeline approaches. Trained on synthetically generated multilingual data with strategic inpainting, it achieves superior visual quality and lip sync across varied motion scenarios.

People

Emerging Technologies

Katakko: Embodiment of Modular Robots through Automatic Motion Mapping

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper presents Katakko, a modular robot system that enables users to create and embody personalized social agents. Katakko provides communication-oriented modules (display, actuator, mobile, and sensor) and an optimization-based algorithm that automatically generates joint-to-joint mappings between the user's body and an arbitrarily assembled robot, with incremental updates upon reconfiguration.

People

Sotaro YOKOI

University of Tokyo

Naoki Shitanda

Kento Matsuo

Takuji Narumi

Khronos Group Networking Reception

Birds of a Feather

Khronos Fast Forward

1:00pm - 2:00pm PDT Monday, 20 July 2026 Room 518

Gaming & Interactive

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Computer Vision

Digital Twins

Education

Games

Generative AI

Graphics Systems Architecture

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionIf you build graphics, XR, 3D, compute, or AI applications, the Khronos Group is helping shape the open standards behind the tools, engines, devices, and platforms you use every day. Kick off your SIGGRAPH week with Khronos Fast Forward, a rapid fire look at the latest advances in Vulkan, Slang, OpenXR, glTF, ANARI, WebGL, machine learning, and AI. Discover what is new, what is next, and where to dive deeper throughout the week through BOFs, talks, demos, and technical discussions.

People

Birds of a Feather

6:00pm - 9:00pm PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

Research & Education

Industry Insight

Full Conference Supporter

Full Conference

Experience

DescriptionCap off a full day of Khronos Working Group updates and technical deep-dives with the annual Khronos Networking Reception! Join fellow developers, artists, and industry leaders for an evening of great food, drinks, and live sponsor demos. Whether you want to connect with the people behind the standards, explore the latest from our sponsors, or simply recharge with the community after a packed day of BOFs, this is the place to be. All are welcome!

People

Lisie Aartsen

THE KHRONOS GROUP

Technical Paper

Kinematic Kitbashing

11:25am - 11:35am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionKinematic Kitbashing synthesizes articulated 3D objects by assembling reusable parts according to an abstract kinematic graph. It preserves plausible attachments across motion using kinematics-aware geometric cues and can optimize for functional goals, enabling new articulated designs from existing part libraries.

People

Minghao Guo

École de Technologie Supérieure (ÉTS)

Victor Zordan

Clemson University

Sheldon Andrews

Knit Everything: Surfaces, Systems, and the Future of Textiles

Talks

9:40am - 10:00am PDT Sunday, 19 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Digital Twins

Education

Fabrication

Games

Generative AI

Geometry

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWhat if anyone who can draw could knit? This talk follows VARIANT3D’s journey building software, languages, and novel production systems that make 3D knitting a more democratic medium—enabling designers to create and manufacture curved, complex surfaces with unprecedented accessibility and control.

People

William Samosir

VARIANT3D

Spatial Storytelling

LA Folded: A Cybernetic Mirage

12:00pm - 1:00pm PDT Monday, 20 July 2026 Concourse Hall

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionLA Folded: A Cybernetic Mirage is an interactive, generative art installation that re-imagines Los Angeles as a living, ever-evolving digital twin. Conceived for SIGGRAPH 2026, the project bridges LA’s rich cinematic legacy with the frontier of spatial computing. By seamlessly integrating Kinect motion tracking and AI-generated point clouds, it invites participants to co-author a collaborative digital monument. As users input their personal memories and desires of LA, individual landmarks dynamically merge, overlap, and fold into a singular, massive 3D cyber environment—blurring the boundaries between physical presence, collective memory, and cybernetic space.

Credit：
Visual & Interactive Director: Jimmz ZHANG, Digital FUN & TEA Community
Technical Director: Ruokun CHEN, TEA Community & FLARE Lab
Sound Artist: Louzhang, USC School of Cinematic Arts

People

Jimmz Zhang

Digital FUN, TEA Community

Spatial Storytelling

LA Local Artists Showcase

12:00pm - 1:00pm PDT Tuesday, 21 July 2026 Concourse Hall

Art

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThe Spatial Storytelling LED Wall Showcase features a curated collection of short-form digital works by Los Angeles–based artists. Spanning immersive media, experimental film, generative art, and digital storytelling, the showcase highlights creative practices that explore new relationships between narrative, technology, and space.

Join us between sessions and during the dedicated lunch hour to experience these works at architectural scale and celebrate the vibrant artistic community of Los Angeles within the Spatial Storytelling program.

LA Local Artists:

Narae Kim
Artwork Title: Flowly
Learn more: https://www.kimnarae.com

Yara Feghali
Artwork Title: Be.Longing XR

Michaela Ternasky-Holland
Artwork Title: Kapwa
Learn more:
@michaelaternaskyholland / www.michaelaternaskyholland.com
@sisiigodly / https://aaron.work/

Faith “Aya” Umoh
Artwork Title: Noösphere
Learn more: www.FaithAyaUmoh.com

Isabel Beavers
Artwork Title: Aphrodite's Dream
Learn more: www.isabelbeavers.com / @isabelbeavers

Wadooah Wali
Artwork Title: The Obscura Society
Learn more: www.newcanvas.co / www.instagram.com/newcanvas_xr / www.linkedin.com/company/newcanvas

Huntrezz Janos
Artwork Title: AfroHungaria
Learn more: www.huntrezz.com

Scarlett Kim
Artwork Title: BEASTS
Learn more: scarlett.kim

Eugene Yen
Artwork Title: The Evolution of My Rectangles
Learn more: www.eugeneyen.com

Technical Paper

LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction

9:10am - 9:20am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionLagrangianSplats reconstructs physically plausible 3D fluid velocity fields from sparse video by combining divergence-free kernels with Lagrangian Gaussian transport. A sliding-window optimization enables efficient long-range supervision, producing state-of-the-art transport consistency and physical accuracy on synthetic and real fluid datasets.

People

Ningxiao Tao

School of Intelligence Science and Technology, Peking University

Mengyu Chu

State Key Laboratory of General Artificial Intelligence

Baoquan Chen

Large-Scale Photogrammetric Documentation of St. John's Co-Cathedral: A Workflow for Cultural Heritage Preservation

Immersive Pavilion

Landmine/Garden

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionLandmine/Garden is an immersive Mixed Reality experience where visitors step into the role of deminers. By collectively searching for concealed landmines, deactivating them, and uncovering the memories and stories buried within the garden, visitors transform a landscape of danger into one of hope, growth, and remembrance.

People

Art Paper

3:00pm - 3:20pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Generative AI

Image Processing

Modeling

Pipeline Tools and Work

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionCultural heritage sites face threats from climate change, conflict, and degradation. Digital documentation has become a preservation necessity, demonstrated by Notre-Dame's 2019 fire. However, academic photogrammetry research remains disconnected from practical implementation by heritage institutions.

This project demonstrates architectural digitization is achievable using commercial tools. By documenting our methodology we provide professionals with replicable approaches to preserve cultural sites. Computer graphics techniques can directly serve the preservation of cultural heritage.

People

Talks

LatentScore: Sketching Soundscapes with LLM-Distilled Retrieval for Procedural Synthesis

9:20am - 9:40am PDT Sunday, 19 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Digital Twins

Education

Fabrication

Games

Generative AI

Geometry

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionLatentScore turns typed scene descriptions into procedural soundscapes you can steer — running locally on CPU. An open-source Python SDK maps language to structured synth parameters in under a second. See a live audiovisual demo where prompts become sound, palettes, and particles.

People

Prabal Gupta

Rama Labs

Technical Paper

LayerInbetween: Occlusion-Aware Stroke Correspondence and Inbetweening with Automatic Layering

9:50am - 10:00am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionLayerInbetween is an occlusion-aware framework for vector stroke correspondence and automatic inbetweening. It performs automatic layering to guide stroke tracing and correspondence finding for occluded strokes, and to resolve occlusion with layers in the inbetween frames. The vector-based method enables more flexible editing of 2D animation than raster-based video generation.

People

Haoran Mo

The Hong Kong University of Science and Technology (Guangzhou)

Zhongyue Guan

The Hong Kong University of Science and Technology (Guangzhou)

The Hong Kong University of Science and Technology (Guangzhou)

Layouts & Procedural - Interactive Discussion

Computer Animation Festival

Layers In History

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionA group of ants goes on a field trip into deep underground to explore ancient fossils, but their adventure triggers a collapse that turns them into the next layer of Earth's history.

People

Yeoleum Choi

Director

Ohio State University

Technical Paper

10:00am - 10:25am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

Technical Paper

Learned Universal Interoperable Virtual Try-ON

2:40pm - 2:50pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a fully automated 3D virtual try-on system that fits diverse multilayer garments onto arbitrary humanoid characters. Using SMPL as an intermediate proxy, it handles unrigged, non-manifold assets, supports garment resizing, and produces high-quality draping without manual correspondence, shared rigs, or 2D sewing patterns.

People

Cong Cao

Mohamed Bin Zayed University of Artificial Intelligence

Xianhang Cheng

Mohamed Bin Zayed University of Artificial Intelligence

Jingyuan Liu

Mohamed Bin Zayed University of Artificial Intelligence

Yujian Zheng

Mohamed Bin Zayed University of Artificial Intelligence

Zhenhui Lin

Mohamed Bin Zayed University of Artificial Intelligence

Ren Li

Mohamed Bin Zayed University of Artificial Intelligence

SUSTech

Meriem Chkir

Mohamed Bin Zayed University of Artificial Intelligence

Hao Li

Mohamed Bin Zayed University of Artificial Intelligence

Pinscreen

Technical Paper

Learning a Delighting Prior for Facial Appearance Capture in the Wild

2:20pm - 2:30pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionA high-quality facial appearance capture method from casual smartphone videos with a powerful delighting prior.

People

Feng Xu

Learning Computer Graphics via Authentic Engineering Challenges

Educator's Forum

11:05am - 11:25am PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Computer Vision

Digital Twins

Education

Games

Modeling

Pipeline Tools and Work

Rendering

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThis short article introduced our experiences in teaching computer graphics through authentic engineering challenges to student members in an academic makerspace at the University of Hong Kong. It highlights the importance of computer graphics technologies in solving emerging engineering challenges.

People

LEI YANG

Learning for CAD - Interactive Discussion

Technical Paper

11:45am - 12:15pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

Technical Paper

Learning in Motion - Interactive Discussion

3:00pm - 3:30pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds

9:10am - 9:20am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionNEO is a neural framework for fast Laplace-Beltrami spectral analysis on 3D point clouds. Rather than computing eigenvectors with expensive iterative solvers, it predicts low-frequency eigenspaces directly from geometry, enabling near-linear scaling, robustness to irregular sampling, and accurate zero-shot transfer to substantially higher-resolution shapes and downstream spectral tasks.

People

Zherui Yang

Tao Du

Learning Matters. Certification Proves It.

Educator's Day Session

1:45pm - 2:15pm PDT Monday, 20 July 2026 Room 411

Arts & Design

Gaming & Interactive

Production & Animation

Research & Education

Animation

Art

Dynamics

Education

Games

Lighting

Modeling

Real-Time

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionAs the demand for skilled Houdini artists continues to grow across the visual effects, animation, and gaming industries, education programs face increasing pressure to prepare students with both technical expertise and industry-recognized credentials. This session will explore the value of certification at every level of the learning journey, including School, Instructor, and Artist Certifications, and how these programs help establish educational quality, validate skills, and create clearer pathways from the classroom to industry careers.
Attendees will gain insight into how certification benefits students, instructors, and institutions by providing measurable standards of achievement and helping align training with industry expectations. We will discuss the role certifications play in building confidence, enhancing employability, and supporting educational excellence.
The session will also highlight the extensive resources available to support educators teaching Houdini. These include free instructor licenses, curriculum reviews, a dedicated learning management system, and an instructor community designed to foster collaboration and knowledge sharing. In addition, we will showcase ready-to-use teaching materials such as Curriculum-in-a-Box, curated presentations, and other educational resources created to help instructors deliver engaging, effective learning experiences while reducing course development time.
Whether you are an educator looking to strengthen your Houdini program or an institution seeking ways to better support student success, this session will provide practical insights into leveraging certifications and educational resources to create meaningful learning outcomes and career opportunities.

People

Technical Paper

Learning Sewing Patterns via Latent Flow Matching of Implicit Fields

2:30pm - 2:40pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce an implicit representation for sewing patterns using distance fields. Combined with latent flow matching, the model learns distributions over panel geometry and stitching, enabling generation, image-based estimation, and optimization. The framework supports flexible topology and improves accuracy over prior methods.

People

Mohamed Bin Zayed University of Artificial Intelligence

Technical Paper

Learning Sparse Singularities for Cross Field Design

9:50am - 10:00am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionProblem-aware quad mesh design is challenging due to the choice of neural representation. We propose a two-stage strategy: we first learn sparse singularities, follwed by an analytical step to convert the singularities into cross field and the final quad. Thanks to the hybrid neural-analytical strategy, we can achieve a problem-aware quad style, which is beneficial to downstream animation or simulation.

People

State Key Laboratory of CAD & CG, Zhejiang University

Technical Paper

Learning View-Dependent Splatting Kernels

2:20pm - 2:30pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis.

People

Huakeng Ding

Zhanpeng Liu

Fan Pei

Kun Zhou

Hongzhi Wu

LentiMorpho: A Display that Switches Between View-Dependent and View-Independent Modes by Varying Liquid Volume

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionLentiMorpho is a reconfigurable light field display that dynamically switches between view-dependent and view-independent presentation by varying liquid volume within a glass-bead lens array. By physically enabling or disabling optical functionality, the system allows a single display to alternate between individualized and shared visual experiences without permanent optical trade-offs.

People

Rintaro Akiyama

Hosei University

Kouyou Otsu

Mai Kamihori

Yuichi Itoh

Let's Plan in OpVerse: An Immersive XR Experience for Thoracoscopic Lung Nodule Surgery

Takafumi Koike

Hosei University

Immersive Pavilion

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionOpVerse demonstrates the complete journey from CT imaging to surgical intervention using XR technology. Attendees experience patient-specific digital twin visualization and hands-on XR-guided surgical planning on a physical phantom, with preliminary clinical results suggesting a ~15-minute reduction in preoperative planning time.

People

Yi-Ching Lee

Hsien-Yuan Hsieh

Yang-Sheng Chen

Xu-Heng Chiang

Ping-Hsuan Han

Yi-Ping Hung

Jin-Shing Chen

LGBTQI+ and Allies Rainbow Meetup

ACM SIGGRAPH 365

3:30pm - 4:30pm PDT Monday, 20 July 2026 See the Description

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Diversity, Equity and Inclusion

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionJoin LGBTQIA+ attendees and allies for the Rainbow Meetup, a welcoming space to connect, celebrate identity, and find a queer community at SIGGRAPH. To ensure a safe, respectful environment, the ACM Code of Conduct will be strictly enforced. Harassment or non-consensual behavior, including unauthorized photography, will not be tolerated. Come help build community, find support, and learn about the future of the Rainbow Affinity Group.

Event location details are available at the ACM SIGGRAPH Village Booth in the West Hall Lobby.

People

AJ Christensen

NASA Scientific Visualization Studio

Immersive Pavilion

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionYou enter a calm yet unfamiliar world, lying dormant as you arrive. As you explore its surroundings, the world gradually opens up, revealing its light. The more you engage with it, the more you become enveloped in a soothing yet lively awakening, full of surprises.

People

Aria Wolf

Cyril Fischer

Christoph Mohr

Sam Matsa

Jakob Bock

Janina Zlotos

Vadim Ivanovs

Maksym Gontov

Lifting Lines and Tone: Image-Space Stylization in Path-Space

Technical Paper

9:00am - 9:10am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a framework for lifting image-space stylizations into path-space rendering, and demonstrate it on line and tone rendering. By constructing geometric mappings between image and path space, our method preserves line and tone structure under complex light transport, enabling coherent, expressive non-photorealistic rendering within the stylized rendering equation.

People

Rex West

Sayan Mukherjee

Yonghao Yue

Light Architecture: Translating the AI Black Box into Immersive Experience

Art Paper

2:00pm - 2:20pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Capture/Scanning

Computer Vision

Display

Ethics and Society

Generative AI

Hardware

Image Processing

Physical AI

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionAs AI becomes an opaque "Black Box," Light Architecture physically "translates" invisible algorithmic structures instead of merely exploiting generative outputs. Synthesizing kinetic light and spatial audio into a Gesamtkunstwerk, this "Experiential AI" offers a sensory alternative to traditional Explainable AI (XAI), providing a critical framework for demystifying the "Hyperobject" of modern computation. Reclaiming agency requires a visceral, embodied encounter with technological systems rather than just intellectual analysis.

People

Yiyun Kang

Yiyun Kang Studio

Korea Advanced Institute of Science and Technology (KAIST)

Educator's Forum

Light Field Cinematography (and the Birth of a Volumetrics Lab)

2:20pm - 2:40pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Capture/Scanning

Education

Ethics and Society

Generative AI

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis talk explores Light Field Cinematography through the development of an interdisciplinary Volumetrics Lab supporting faculty-led undergraduate research. Bridging computer science, real-time graphics, cinematography, and embodied performance, it demonstrates how motion-based volumetric capture enables new forms of cinematic, computational, and conceptual problem solving through spatial engagement within real-world educational constraints.

People

C. K. Olsen

University of Iowa

Technical Paper

Light Transport - Interactive Discussion

3:00pm - 3:30pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

Technical Paper

LightOpt: Lights Optimization for Real-time Rendering

4:05pm - 4:15pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Games

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionLightOpt is a differentiable optimization framework that automatically reduces the number of lights in real-time game scenes while preserving visual appearance. By optimizing and restructuring real-time light sources, it lowers lighting cost, reduces overlap, and improves cross-platform performance for modern game rendering.

People

Technical Workshop

Lines and Minds: Visual Abstraction in Art, Psychology, and Computer Graphics

2:00pm - 5:15pm PDT Sunday, 19 July 2026 Room 406 AB

Arts & Design

Research & Education

Art

Artificial Intelligence/Machine Learning

Computer Vision

Education

Generative AI

Image Processing

Industry Insight

Rendering

Scientific Visualization

Full Conference Supporter

Full Conference

DescriptionVisual abstraction --- from sketches and diagrams to icons and comics --- enables people to communicate, express, and create by distilling complex visual information into simplified forms that preserve essential meaning. These simplified forms support perception, reasoning, and communication in ways that detailed depiction often cannot. Visual abstraction has been studied across cognitive science, art theory, and computer graphics, offering complementary perspectives on how humans perceive, produce, and interpret such representations.

This workshop brings together these perspectives to examine abstraction as a cognitive mechanism, a communicative tool, and a computational challenge, exploring questions such as: Why and how do people abstract? What makes a simplification effective? How can machines learn to abstract in ways aligned with human perception? And as AI excels at generating realistic images, what role might abstraction play in how humans and AI create together?

People

Yael Vinker

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Mia Tang

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Kartik Chandra

Technical Paper

LLM-enhanced Scene Graph Learning for Household Rearrangement

9:00am - 9:10am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present an LLM-enhanced scene graph framework for autonomous household rearrangement. By transforming scene graphs into affordance-enhanced graphs that encode scene-grounded object functionality and user preferences, our method detects misplaced objects and plans correct placements. We demonstrate state-of-the-art performance with an end-to-end robotic system in simulated and real-world environments.

People

Wenhao Li

Shilong Zou

Zhinan Yu

Zheng Zhou

Wenxuan Li

Chenyang Zhu

Institute of AI for Industries Chinese Academy of Science

Ruizhen Hu

Shenzhen University

Kai Xu

Wenhao Li

National University of Defense Technology (NUDT)

Technical Paper

LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending

2:00pm - 2:10pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionLoBoFit brings robust, high-fidelity garment refitting to challenging avatar changes. It preserves original design features, fine wrinkles, and fit style by optimizing garments in blended local bone coordinates, enabling stable convergence, efficient refinement, and reliable results across large body variations, arbitrary poses, and both single- and multi-layer clothing.

People

Meng Zhang

Nanjing University of Science and Technology

Yu Xin

Nanjing University of Science and Technology

Feiya Guo

Kaizhang Kang

King Abdullah University of Science and Technology (KAUST)

Technical Paper

Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations

2:50pm - 3:00pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a GPU system for automatic differentiation for functions defined on triangle meshes that exploits locality and sparsity to deliver efficient derivative computation. From simple user-defined energy terms, the system produces gradients, Jacobians, and sparse Hessians, accelerating simulation and optimization workflows and shifting the computational bottleneck away from differentiation.

People

Ahmed Mahmoud

Rahul Goel

Jonathan Ragan-Kelley

LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models

Technical Paper

2:30pm - 2:40pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Lighting

Full Conference Supporter

Full Conference

DescriptionThis work introduces long-horizon event-based video generation, a challenging task prone to severe temporal inconsistency, and presents LongE2V, a novel approach leveraging video diffusion priors to jointly handle video reconstruction, prediction, and frame interpolation, recovering high-quality videos from sparse event streams.

People

Cheng-De Fan

Chun-Wei Tuan Mu

Chen-Wei Chang

Chin-Yang Lin

Kun-Ru Wu

Yu-Chee Tseng

Yu-Lun Liu

LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization

Technical Paper

11:25am - 11:35am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionLooseRoPE enables prompt-free image editing by letting users crop and paste objects directly into new scenes. It improves diffusion-based harmonization by modulating RoPE with saliency, balancing identity preservation and contextual blending. This yields intuitive, spatially precise edits that maintain object appearance, pose, and placement without requiring text prompts or masks.

People

Appy Hour

Lost Spirits: An Interactive Encounter with a Fractured Soul

5:00pm - 7:00pm PDT Wednesday, 22 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Games

Generative AI

Geometry

Image Processing

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionLost Spirits is an interactive game prototype exploring emotionally resonant local AI characters on edge devices. The player acts as a medium, helping a fractured ghost reconstruct her identity. Built via an AI-augmented workflow, the experience allows players to guide the spirit’s evolution toward final redemption or condemnation.

People

Angela Wu

San Jose State University

Computer Animation Festival

Games Summit

Love & Gold

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionTwo thieves enter the same dungeon searching for a gem worth incredible wealth, but what they find along the way is worth more than all the treasure in the dungeon combined.

People

Connor Van Dyke

Director

Brigham Young University

Jaysen Duckworth

Producer

Brigham Young University

Technical Paper

Low-Rank Koopman Deformables with Log-Linear Time Integration

11:25am - 11:35am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a Koopman operator method for fast deformable simulation using Dynamic Mode Decomposition, enabling efficient long-term prediction without sequential time stepping. Our discretization-agnostic formulation generalizes across shapes and resolutions, making Koopman-based reduced models practical for geometry variation, control, and fast shape optimization tasks.

People

Yue Chang

Peter Yichen Chen

Eitan Grinspun

Maurizio M. Chiaramonte

LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography

Technical Paper

2:10pm - 2:20pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

DescriptionMaster the night with LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography. Merging flare disentanglement and generative diffusion, our framework conquers entangled degradations. LUCID unlocks continuous control over global illumination and light source scale, enabling the brightening of deep shadows while strictly preventing light pollution.

People

Tingyu Yang

Yuan Cheng

Xiaoyun Yuan

Lucky High Dynamic Range Smartphone Imaging

Technical Paper

2:20pm - 2:30pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

DescriptionStage 3 revisions add a DNG-to-sRGB pipeline description and ISP-limitation caveat, promote six supplement figures/tables to the main paper, clarify use of unseen handheld captures for real-world evaluation, added a failure case, limitation and future work in the main paper, and add supplementary motion statistics and a no-motion HDR+ comparison.

People

Computer Animation Festival

Games Summit

Luma

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionIn a Solarpunk Universe, Ren and Cora’s peaceful life is shattered by an odd phenomenon spreading through water. They have to go on an adventure to find the source of it and save their ecosystem.

People

Director

Director

Director

Director

Director

Director

Director

Director

Director

Technical Paper

M-ABD: Scalable, Efficient, and Robust Multi-Affine-Body Dynamics

10:45am - 10:55am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a multibody simulation framework leveraging affine body dynamics with a co-rotational formulation, enabling pre-factorized system matrices under implicit integration. Mapping primal coordinates onto a dual space via KKT, our method exactly enforces joint constraints, achieving interactive rates for hundreds of thousands of bodies on a single CPU core.

People

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Yili Zhao

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Hao Su

Peter Yichen Chen

MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

Technical Paper

9:20am - 9:30am PDT Monday, 20 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionMACE-Dance generates dance videos from music using cascaded motion and appearance experts. It first produces expressive 3D dance motion from music, then animates a reference image into a temporally coherent video. The paper also introduces MA-Data, a large-scale dataset and evaluation protocol for this task.

People

Kaixing Yang

Xiangyue Zhang

Puwei Wang

Machine Choreographies: AI, Dance, and the Future of Embodied Performance

Birds of a Feather

5:00pm - 5:30pm PDT Sunday, 19 July 2026 Room 510

New Technologies

Art

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

Experience

DescriptionMachine Choreographies: AI, Dance, and the Future of Embodied Performance explores how artificial intelligence is reshaping movement, creativity, and the body in motion. This Birds of a Feather session invites artists, technologists, and researchers to exchange ideas, tools, and provocations around co-creation with machines. From live performance capture to GenAI video, generative choreography, responsive environments, and embodied interaction, we will discuss emerging practices and critical questions. How does AI change authorship, presence, and expression in dance? What new aesthetics and ethics emerge? Join this informal gathering to share projects, spark collaborations, and imagine future forms of hybrid human-machine performance.

People

Noshaba Cheema

DFKI

Llogari Casas

Spatial

Alexandra Schmucklermann

Ye Pan

Saarland Informatics Campus

Kenny Mitchell

Machine Civilization: Exploring Machine Alterity through a Generative Semiotic Installation

Creative Cridhe

Art Paper

2:20pm - 2:40pm PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Capture/Scanning

Computer Vision

Display

Ethics and Society

Generative AI

Hardware

Image Processing

Physical AI

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionMachine Civilization offers SIGGRAPH community a critical lens for examining the gap between explainability and intelligibility in the age of intelligence. This work explored non-human meaning-making and comprehension limits in human-machine interaction. It raises an ethical question: can we engage with machine intelligence as genuine alterity rather than tools? This research proposes that recognizing the alterity of machine intelligence and rethinking de-anthropocentric innovation may be essential for AI's next stage.

People

Jia-Qi Shi

Hong Kong University of Science and Technology, Guangzhou

Yixiong Wang

Hong Kong University of Science and Technology, Guangzhou

Jiawen Zheng

Hong Kong University of Science and Technology, Guangzhou

Hourun Wang

Hong Kong University of Science and Technology, Guangzhou

Yufeng Zeng

Hong Kong University of Science and Technology, Guangzhou

Chen Liang

Hong Kong University of Science and Technology, Guangzhou

Birds of a Feather

Machine Learning, Neural Rendering, and the Future of Open Graphics

1:00pm - 1:30pm PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Graphics Systems Architecture

Hardware

Industry Insight

Physical AI

Real-Time

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionAs AI and real time graphics continue to converge, the Khronos Group is helping build an open, cross platform foundation for scalable machine learning and neural graphics. Join us for an interactive discussion on insights from the Khronos AI Ecosystem Research Project, emerging industry trends, and the growing role of Vulkan and Vulkan ML in enabling portable AI acceleration. Explore use cases including neural shaders, on device inferencing, neural rendering, and efficient graphics pipelines. Bring your questions, share your perspective, and help shape the future of open AI for interactive 3D.

People

Markus Tavenrath

Making ChikaBOOM!: AI, Animation, and the Artist-Centered Production Pipeline

Industry Session

1:00pm - 1:50pm PDT Thursday, 23 July 2026 Room 502A

New Technologies

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Generative AI

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionChikaBOOM! offers a timely case study in how generative AI is being used inside a real animation production pipeline. Written and directed by c. Craig Patterson, the short follows aspiring young magician Chika Batstone as she accidentally unleashes a chaotic magical creature into New York City. In this session, Patterson will unpack how AI supported the making of the film, from creative development and visual exploration through production iteration and final frames. The session will focus on the practical realities of AI-assisted production: what worked, how teams maintained creative control, and what lessons apply to studios, artists, technologists, and production leaders building AI into animation workflows.

People

Industry Session

Making the Old Stories New: Innovative Dreams and Moses

11:00am - 12:00pm PDT Thursday, 23 July 2026 Room 502A

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Generative AI

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionThe Old Stories: Moses revisits one of the most enduring stories ever told. In this talk, Innovative Dreams shares how its artists and filmmakers approached the making of Moses, using real-time hybrid filmmaking to move from imagination to image with greater speed and flexibility. The team connects performance, virtual environments, and real-time creative iteration to shape atmosphere, scale, and emotional clarity. The session is less about technology as spectacle, and more about the craft of making an ancient story feel immediate, intimate, and alive.

People

Jon Erwin

WONDER PROJECT; INNOVATIVE DREAMS

Tim Moore

Vū Technologies

Technical Paper

Manifold k-NN: Accelerated k-NN Queries for Manifold Point Clouds

2:40pm - 2:50pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present Manifold k-NN, a dynamic programming-based framework for accelerated k-nearest neighbor search on manifold point clouds. By recursively partitioning insertion history via Voronoi successor lists, our method achieves 1–10× speedup over kd-trees in volume-to-surface queries, while supporting zero-overhead prefix queries and dynamic point deletion.

People

Qingdao University of Science and Technology

Technical Paper

MAOAM: Unified Object and Material Selection with Vision-Language Models

11:35am - 11:45am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Augmented Reality

Generative AI

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionMAOAM is a unified selection framework that enables precise object- and material- level selection across both text- and click-based interactions. MAOAM leverages a VLM which interprets the user's selection intent, and encodes information to the segmentation head. MAOAM achieves strong performance and generalization across varied objects, materials, and prompting scenarios.

People

Jaden Park

Michael Fischer

Mapping, Untangling & Summarizing Surfaces - Interactive Discussion

Technical Paper

4:35pm - 5:05pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Geometry

Modeling

Full Conference Supporter

Full Conference

Technical Paper

MAROON: A Dataset for the Joint Characterization of Near-Field High-Resolution Radio-Frequency and Optical Depth Imaging Techniques

2:10pm - 2:20pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

DescriptionRobust perception benefits from complementary sensors, yet close-range setups remain scarce. We characterize optical and near-field radar imagers via multimodal calibration, collecting data from RGB-D sensors and one mmWave MIMO radar. We evaluate depth sensing across materials, geometries, and distances, release MAROON, and show applications in inverse rendering and reconstruction.

People

Vanessa Wirth

Johanna Bräunig

Nikolai Hofmann

Martin Vossiek

Tim Weyrich

University College London

Marc Stamminger

Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

Vanessa Wirth

Art Paper

Materiality and Computation Q&A, Art Paper Reflections, and 2027 Preview: 20 min

5:45pm - 6:00pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Display

Education

Fabrication

Generative AI

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Robotics

Full Conference Supporter

Full Conference

Experience

DescriptionAfter all the presentations, attendees are encouraged to engage in a Q&A session to discuss the topics presented. This will be followed by an Art Papers wrap-up, summarizing key insights, and a preview by the SIGGRAPH 2027 Art Papers chair, offering a glimpse into the upcoming 2027 Art Papers program.

Technical Paper

Materials & Textures - Interactive Discussion

11:45am - 12:15pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

Birds of a Feather

MaterialX and OpenPBR

1:30pm - 3:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 3

Production & Animation

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionJoin MaterialX and OpenPBR Technical Steering Committee members and contributors as they share recent milestones, future plans and answer questions from the community.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Jonathan Stone

MaterialX

Technical Paper

Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes

10:55am - 11:05am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionThis paper tackles the task of learning to generate signals over triangle meshes in a triangulation-agnostic manner, meaning the trained model can be applied to different mesh triangulations effectively. It proposes a specific noise distribution which is triangulation agnostic on meshes, to be used inside the Flow Matching's denoising process.

People

Tianshu Kuai

University of Montreal

University of Montreal

Mila

Technical Paper

MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation

4:05pm - 4:15pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Games

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionMAViD is a multimodal framework for interactive audio-visual dialogue. Its Conductor-Creator architecture integrates multimodal understanding and reasoning into response generation. By combining AR and diffusion models, MAViD enables synchronized, long-duration audio-video generation with consistent identity and timbre, delivering vivid and contextually coherent digital human interactions.

People

Technical Paper

Mechanical Cloaking of Halftoned Imagery

4:05pm - 4:15pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe explore a new direction in mechanical cloaking: halftoning an image using a porous structure that behaves like a linear, isotropic material and visually matches an image. For an external observer, this creates the surprising effect where the object appears mechanically homogeneous while its porous structure resembles a target image.

People

Jonàs Martínez

Inria

Brisard Sébastien

Aix Marseille Université

Kostas Danas

LMS, CNRS, Ecole Polytechnique

ACM SIGGRAPH 365

Meet Mingle and Make a Difference

9:00am - 9:45am PDT Tuesday, 21 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin us for a relaxed and informative mingling event designed for those interested in exploring volunteering opportunities within the ACM SIGGRAPH organisation and in SIGGRAPH Conferences. This is a great chance to meet current key volunteers and leadership, learn about the various roles and committees that you could get involved in, and discover how your skills and passions could make a meaningful impact to our community. Whether you're looking to expand your professional network, gain new experiences, or give back to the community, this event provides a valuable opportunity to get involved with SIGGRAPH!

People

Mashhuda Glencross

University of Queensland

Technical Paper

MegaNorm: Local Patches Embedding for Efficient and Robust Point Normal Orientation at Super-Large Scale

11:25am - 11:35am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionMegaNorm is a fast, accurate, and robust method for orienting normals in non-watertight, scene-scale point clouds, scaling to ~50M points in under 10 minutes. It uses two feed-forward networks: one orients local patches in parallel, while a lightweight MLP evaluates pairwise consistency. Finally, a 0–1 integer program enforces global consistency.

People

Zhuodong Li

Zengke Liu

Xuhui Chen

Wencheng Wang

Memory and Heritage - Q&A

Art Paper

3:20pm - 3:30pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

Animation

Art

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Generative AI

Image Processing

Modeling

Pipeline Tools and Work

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAfter all the presentations, attendees are invited to participate in a Q&A.

Technical Paper

MeshFEM: A Block-accelerated Solver for Nonlinear Finite Elements

3:45pm - 3:55pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a high-performance Newton-type solver designed for the nonlinear finite element problems common in simulation and geometry processing. By leveraging the inherent block structure of spatially discretized systems across all solver phases, we achieve significant speedups over existing direct-solver-based frameworks without compromising accuracy, flexibility, or ease of use.

People

Haleh Mohammadian

Xinzhuo Hu

Roi Poranne

University of Haifa

Julian Panetta

MeshFlow: Mesh Generation with Equivariant Flow Matching

Technical Paper

11:35am - 11:45am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionMeshFlow is a powerful diffusion-based framework utilizing equivariant modeling to transform random triangle soups into high-quality meshes in less than one second.

People

Qi Sun

Guandao Yang

Computer Animation Festival

Metachess: The Genesis

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionMetachess is a generative system that translates chess games into spatial structures. Using PGN chess notation as input, parses each move and transforms strategic decisions into a growing architectural form. As the game unfolds, moves become trajectories, accumulating into a three-dimensional structure.
The second work visualizes the historic 1997 rematch between world chess champion Garry Kasparov and IBM’s Deep Blue, a milestone in the history of artificial intelligence. Through the Metachess system, the game is no longer represented as notation or replay, but as a spatial trace of strategy emerging in time.
Each game produces a unique structure that can also be fabricated through metal additive manufacturing. The system can operate in real time, translating live matches into evolving forms. Metachess proposes a new way of reading games as architectural patterns of decision-making, where players shift from opponents to co-creators of a shared spatial artifact.

People

Alexandros Kesisoglou

Founder

MiniMax | New Frontier in Multimodality

Stage Session

4:00pm - 4:30pm PDT Wednesday, 22 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Games

Generative AI

Image Processing

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionDriven by the mission to co-create intelligence with everyone, MiniMax is dedicated to accelerating the path to AGI. Through independently developed foundation models, MiniMax enables the seamless integration of text, audio, image, video, and music. This session will unveil a new frontier in multimodality, exploring how these cross-modal capabilities redefine the future of next-generation creative workflows and intelligent experiences.

People

Victor Su-Ortiz

MiniMax

Technical Paper

Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation

10:45am - 10:55am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present Mix3R, a method that mixes feed-forward reconstruction and generative 3D priors using a Mixture-of-Transformer architecture for multi-view aligned generative 3D reconstruction from sparse views.

People

Beijing Normal University

Technical Paper

Mixed Material Point Methods for Stiff Elastoplasticity

10:55am - 11:05am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionOur variant of the Material Point Method discretizes both the velocity and stress fields over mixed finite elements, avoiding the need for repeated costly particle-to-grid transfers within the implicit elastoviscoplastic solve. Our method supports materials ranging from sand and snow to elastic solids, with two-way coupling to rigid-body solvers.

People

Gilles Daviet

Mixing Colors: Exploring Digital Images through the Bayer Filter

Educator's Forum

11:25am - 11:45am PDT Wednesday, 22 July 2026 Room 501 ABC

Gaming & Interactive

New Technologies

Research & Education

Augmented Reality

Digital Twins

Education

Games

Image Processing

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis Bayer Filter assignment introduces digital image formation concepts in undergraduate Computer Graphics courses while playing with different components of light and color. Students get visual feedback as they take a deep, step-by-step dive into working with digital image data structures combining flashlights, worksheets, code, and photographs.

People

Brittany Morago

University of North Carolina Wilmington

Technical Paper

Mixwell: Sharp 2D Fluid Brushes for Progressive Physics-Based Mixing

11:35am - 11:45am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionMixwell introduces sharp 2D fluid brushes and GPU-accelerated analytical methods for progressive, resolution-independent physics-based mixing. Derived from potential flow around cylindrical tines, Mixwell evaluates drift per sample without grids or intermediate resampling, enabling real-time, arbitrary-resolution fluid mixing and rendering with negligible numerical dissipation.

People

Technical Paper

Mobile3DGS³: Accelerate Mobile 3DGS Rendering via Gradient-Aware Super-Sampling and Frame Interpolation

2:50pm - 3:00pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose Mobile3DGS³, the first mobile 3DGS acceleration paradigm solving high-res real-time rendering pain points via gradient-assisted post-rendering. It features TSGC, GASS, GAFI for alternating super-sampling/interpolation, delivering high-fidelity efficiency.

People

Fan Gao

YIbo Zhao

Changhao Song

Jiarui Wen

Yuxuan Song

Youcheng Cai

MOCHI: Motion Enhancement of Collaborative Human-object Interactions

Technical Paper

2:40pm - 2:50pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionOur method enhances noisy multi-human object interaction (MHOI) data by automatically generating plausible hand and finger motions and refining noisy body movements, all while preserving the original interaction semantics.

People

Jiye Lee

Yonghun Choi

Jungdam Won

Modernizing the Glacier Render Architecture for 007 First Light

Talks

4:45pm - 5:05pm PDT Sunday, 19 July 2026 Room 403 B

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Games

Geometry

Hardware

Image Processing

Performance

Pipeline Tools and Work

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionThe talk covers transitioning to a render dependency graph implementation with automatic memory management, GPU synchronization, and async compute scheduling, along with a rich suite of debug tools — including a real-time frame analysis tool. Case studies include raytracing acceleration structures and terrain virtual texturing.

People

Owen Angell

IO Interactive

Computer Animation Festival

Games Summit

Monitor

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionA story of early parenthood that preys on the fears of new parents. Someone is always watching…

Monitor is an independent short film from Michael Berardini, a Director of Scrat Tales and Batwheels. The short is done in a unique style blending 2D characters in a 3D environment to give the entire film an illustrative quality. Batu Sener (Scrat Tales, Better Man) delivers a beautiful but haunting score while Jérémy Ben Ammar provides a quietly creepy soundscape.

People

Michael Berardini

Director, Animator

No affiliation

Birds of a Feather

Montage as Pedagogical Scaﬀold for Reasoning Beyond Language

4:00pm - 5:00pm PDT Tuesday, 21 July 2026 Room 512

Research & Education

Art

Education

Ethics and Society

Image Processing

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionMultimodal reasoning models have introduced a disruptive, still-insufficiently elaborated shift in how students learn and create–functioning as what some might call a "collaborative partner." The crux of the issue, however, is that this human-machine interaction carries an inherent asymmetry: the machine holds a partial view of context, stakes, and tacit/embodied knowledge involved.

This BoF gathers practitioners to share strategies for working and teaching in algorithmically opaque creative environments. As an opening provocation, we'll explore possibilities latent-space visualization tools bring for latent-space navigation, then open the floor: What tacit knowledge manifests here? What pedagogies are emerging in your practice?

People

Xiaodi Tang

Robert Rapoport

University of Lüneburg

David Lin

Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions

Technical Paper

4:05pm - 4:15pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionThis paper extends Monte Carlo PDE solvers to handle nonlinear radiative boundary conditions using a Picard-style fixed-point iteration framework. It introduces a heteroscedastic regression-based denoising method for boundary estimates and demonstrates the approach on heat radiation simulations with complex geometries, achieving higher accuracy than standard linearization strategies.

People

Anchang Bao

Enya Shen

Haihe Lab of ITAI

Jianmin Wang

Monte Carlo Rendering of Biharmonic Diffusion Curves

Technical Paper

11:05am - 11:15am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionBiharmonic diffusion curves are lightweight vector graphics primitives that offer artistic control over color gradients. We present their first Monte Carlo renderer, which builds upon recent advances in Monte Carlo geometry processing. We phrase the biharmonic problem as two coupled second-order problems and recover boundary data using variational energy minimization.

People

Paul Himmler

Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

Tobias Günther

Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

Birds of a Feather

MoonRay

11:00am - 12:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionASWF migration update, presentations and demos, roadmap and open discussion.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Randy Packer

DreamWorks Animation

Technical Paper

MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization

4:15pm - 4:25pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionMoonSplat is a robust and efficient online voxelized 3DGS reconstruction framework integrated with global Sim(3) optimization, which enables reliable camera tracking and efficient global loop closure for both camera poses and voxelized 3DGS. MoonSplat is equipped with a color residual learning strategy for real-time online optimization of voxelized 3DGS.

People

Beijing Hydrogen Intelligent Tech. Co., Ltd.

Yao Zhang

Beijing Hydrogen Intelligent Tech. Co., Ltd.

Hui Zhou

Beijing Hydrogen Intelligent Tech. Co., Ltd.

Zhouhui Lian

MorphSkein: A Shape-Changing Afterimage Display Preserving Pixel Density During Surface-Area Changes Across Troposkein-Based Shapes

Technical Paper

11:35am - 11:45am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionShape-changing displays typically lose pixel density as surface area expands, limiting usability. We introduce MorphSkein, a shape-changing afterimage display that preserves a minimum density (1.44 px/cm in our prototype) across naturally occurring axisymmetric shapes of varying surface area generated by spinning cables (troposkeins).

People

Maxime Daniel

ESTIA Institute of Technology

Shariff AM Faleel

Pourang Irani

Motion Generation, Warping & Control - Interactive Discussion

Birds of a Feather

Motion Capture Society

11:00am - 12:00pm PDT Wednesday, 22 July 2026 Room 512

Production & Animation

Animation

Capture/Scanning

Games

Hardware

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionOpen to everyone who has an interest in Motion Capture. We'll discuss various hardware and software solutions, pipelines and techniques for getting the best data, performance, shoot day, and production pipeline. This is not specific to any one vendor or technology. All are invited!

People

Troy McFarland

Lane Community College

Technical Paper

3:00pm - 3:30pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Motion Transfer & Inbetweening - Interactive Discussion

10:00am - 10:30am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Motion4Motion: Motion Transfer Across Subjects at Inference

9:00am - 9:10am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionThis work proposes a novel framework, Motion4Motion, for transferring a motion from one subject to another in a video. Without a skeleton or neural network training, Motion4Motion runs efficiently at inference.

People

MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives

Technical Paper

2:20pm - 2:30pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionMotionBricks is a real-time generative framework that transforms interactive motion control for animation and robotics. By combining a large-scale latent backbone with intuitive "smart primitives," it delivers high-quality, zero-shot motion synthesis at 15,000 FPS, allowing users to effortlessly build complex and fine-grained animations and robotic applications.

People

Yuke Zhu

Simon Yuen

Mountless Aerial HMDs: Designing Non-Wearable HMD Experiences Based on Aerial Imaging Optics

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a non-wearable VR system that forms stereoscopic aerial images in front of the user. By eliminating head-mounted devices, our mountless aerial HMD enables quick, comfortable transitions between physical and virtual spaces, offering a new design space for immersive VR experiences.

People

Shogo Fukushima

Kyushu University

Immersive Pavilion

MoveTogether: Exploring Physical Co-op Gameplay in Co-located Mixed Reality via Modular Shared Props

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionMoveTogether, a novel physical co-op gameplay in which two players manipulate a single tracked prop, creating a shared physical communication channel that complements visual and audio cues. We showcase the modular prop kit MingleKit through the game TimberLand, a sequence of short cooperative challenges that encourages players to explore coordination.

People

Zi-Yun Lai

National Chengchi University

Po-Chuan Huang

Pin-Yu Chen

National Taiwan University of Science and Technology

Shu-Chen Liu

Ching-I Huang

National Taiwan University of Science and Technology

Chih Heng Tam

Neng-Hao Yu

National Taiwan University of Science and Technology

Mike Y. Chen

Department of Design, National Taiwan University of Science and Technology

Ying-Hsuan Li

Course

Moving Mobile Graphics

2:00pm - 5:15pm PDT Wednesday, 22 July 2026 Petree D

Gaming & Interactive

Artificial Intelligence/Machine Learning

Games

Hardware

Lighting

Performance

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionA technical introduction to mobile graphics spanning the spectrum of hardware, software and developer experience, exploring the state of the art. We look at how neural graphics, GPU-driven rendering, global illumination and ray tracing techniques are being brought to mobile.

People

Rodrigo Holztrattner Reis

Technical Paper

mpcGear: Multi-Point Conjugation Gear Mechanisms

11:15am - 11:25am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionThis work presents a new class of gear mechanisms, called multi-point conjugation gear mechanisms, as well as computational techniques to modeling these gear mechanisms for exactly generating user-specified 3D motions under external loads.

People

Ke Chen

Joshua John Shi Kai Lee

Jianmin Zheng

Peng Song

MPM Lite: Linear Kernels and Integration without Particles

Technical Paper

11:05am - 11:15am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionMPM Lite is a hybrid Lagrangian/Eulerian method that removes particle-based quadrature at solve time. It achieves 15.9 times speedup over implicit MPM, and 1.88 times speedup over explicit MPM.

People

Xiang Feng

Yunuo Chen

Chang Yu

Hao Su

Demetri Terzopoulos

Toyota Research Institute

Joe Masterjohn

Alejandro Castro

Toyota Research Institute

MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors

Technical Paper

10:45am - 10:55am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionMTPano is a robust multi-task foundation model for panoramic scene understanding. Trained via a label-free pipeline using perspective dense priors, it adopts a dual-stream architecture that resolves feature conflicts between depth, segmentation, and surface normal estimations, achieving state-of-the-art performance on spherical images.

People

Multi-feature Radiance Baking Neural Networks for Instant Volumetric Rendering

Technical Paper

2:30pm - 2:40pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose MRBNN that delivers real-time photorealistic volume rendering. We leverage reformulation of in-scattering integral and design an efficient neural representation and sampling strategy. Our method achieves rendering in a few milliseconds with the ability to handle complex cases such as spatially varying albedo and heterogeneous phase.

People

Technical Paper

Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion

9:40am - 9:50am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis work addresses disocclusion noise in ReSTIR by extending the framework to multiple screen-space layers. This enables occluded samples in previous frames to contribute to the final image, improving temporal reuse in disoccluded regions. Depth ranges and active domains are introduced to reduce computational overhead while maintaining quality.

People

Technical Paper

MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance

2:40pm - 2:50pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionText-to-motion models struggle with composite prompts, often collapsing to a single action. We present MultiAct, an inference-time, unpaired framework that enhances pretrained generators by amplifying cross-attention for underrepresented tokens. A lightweight decision scheme selects optimal parameters per prompt, improving semantic coverage while preserving motion realism without retraining or architectural changes.

People

CYENS Centre of Excellence

Sigal Raab

Tel Aviv University

Technical Paper

Multimodal Learning - Interactive Discussion

4:45pm - 5:15pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Games

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

MUSIC: Learning Muscle-Driven Dexterous Hand Control

2:30pm - 2:40pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a data-driven framework for physics-based, muscle-driven dexterous control that enables musculoskeletal hands to perform piano playing for novel musical scores. Our framework adopts a hierarchical architecture, combining high-frequency muscle control with low-frequency coordination. The method achieves coordinated bimanual motions and produces human-like activation patterns, generalizing beyond reference data.

People

Technical Paper

MV-S2V: Multi-View Subject-Consistent Video Generation

2:00pm - 2:10pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Rendering

Full Conference Supporter

Full Conference

DescriptionMV-S2V is the first work to explore video generation with multi-view subject consistency. It presents a simple yet effective framework, including a tailored data curation pipeline and a Temporally-Shifted RoPE (TS-RoPE) specially designed for multi-view reference conditioning, achieving superior 3D subject consistency w.r.t. multi-view reference images and high-quality visual outputs.

People

Ziyang Song

The Hong Kong Polytechnic University

Xinyu Gong

Bangya Liu

Zelin Zhao

NanoSkin: Human Skin Super-Resolution and Material Acquisition for Photorealistic Digital Doubles at Scale

Stage Session

11:30am - 12:00pm PDT Tuesday, 21 July 2026 West Hall A

New Technologies

Production & Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Digital Twins

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionWe will present NanoSkin, our approach for increasing the resolution of actor-specific skin microdetail by a factor of 4 to 16. NanoSkin is a neural network trained on our proprietary skin dataset to generate displacement textures up to 16K.
Skin microdetail is one of the key factors that contributes to the realism of digital characters. However, one of the most common production approaches is still to use pre-made skin detail maps captured from other people. We will give a high-level overview of the approach we use to enhance the details of a specific actor, rather than inventing them from scratch or transferring them from another person.
We will also discuss our work on lookdev automation and automatic material map acquisition, where texture maps are estimated in a way that allows the rendered character to match the actor’s reference photographs as closely as possible.

People

Technical Paper

NeuBase: Spline Surfaces with Neural Basis Functions

2:50pm - 3:00pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce NeuBase, a neural parametric surface representation that both accurately fits target surfaces with fine geometric detail and supports intuitive real time surface deformation.

People

Anshul Mendiratta

Lei Yang

NeuPPS: Neural Piecewise Parametric Surfaces

Technical Paper

2:40pm - 2:50pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present Neural Piecewise Parametric Surfaces (NeuPPS) that models complex surface geometries with a coarse patch layout containing arbitrary n-sided surface patches, offering enhanced flexibility, high fitting precision, and ensured continuity between adjacent patches. Applications to surface fitting and shape space learning tasks demonstrate its advantages over existing methods.

People

Lei Yang

Center for Robotics and Embodied Intelligence (CREO)

Yongqing Liang

Xin Li

Congyi Zhang

Guying Lin

Macau University of Science and Technology

Cheng Lin

Alla Sheffer

Neural Cellular Automata: From Cells to Pixels

Technical Paper

9:20am - 9:30am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

DescriptionWe pair Neural Cellular Automata with a lightweight Neural Field that decodes coarse cell states and local coordinates into high-resolution appearance, decoupling lattice size from output resolution. Trained end-to-end with task-specific losses, our model synthesizes textures and grows morphologies at arbitrary resolution across 2D/3D/mesh in real-time while preserving self-organizing behavior.

People

Alexander Mordvintsev

Technical Paper

Neural Particle Automata: Learning Self-Organizing Particle Dynamics

9:30am - 9:40am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

DescriptionNeural Particle Automata extend Neural Cellular Automata from fixed grids to dynamic particles. Each particle carries a continuous position and internal state, updated by a shared neural rule with SPH-based local perception. Backed by optimized CUDA kernels, NPA learn scalable self-organizing dynamics for morphogenesis, particle texture synthesis, and point-cloud classification.

People

Ehsan Pajouheshgar

EPFL

Hyunsoo Kim

Korea Advanced Institute of Science and Technology (KAIST)

Korea Advanced Institute of Science and Technology (KAIST)

Technical Paper

Neural Quadrature Rule and Autoregressive Adaptive Sampling

4:35pm - 4:45pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionLearnable adaptive sampler and integrator using Transformer.

People

Haolin Lu

Liwen Wu

Zimo Wang

Tzu-Mao Li

Ravi Ramamoorthi

NeuralSketch2Surf: Fast Neural Surfacing of Unoriented 3D Sketches

Technical Paper

11:35am - 11:45am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce NeuralSketch2Surf, the first fast and robust neural surfacing solution, capable of processing arbitrary unoriented sketches at interactive rates.

People

Hongsheng Ye

Anandhu Sureshkumar

Zhonghan Wang

University Grenoble Alpes, CNRS, INRIA, Grenoble INP, LJK

Stefanie Hahmann

Marie-Paule Cani

LIX-Ecole Polytechnique/CNRS

University Grenoble Alpes, CNRS, INRIA, Grenoble INP, LJK

Georges-Pierre Bonneau

Amal Dev Parakkat

Neurodiversity in Computer Graphics, Games, and Interactive Media

Birds of a Feather

1:00pm - 2:00pm PDT Wednesday, 22 July 2026 Room 512

Research & Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionFollowing community discussions at SIGGRAPH 2024 and 2025, this Birds of a Feather session invites educators, industry professionals, students, researchers, and advocates to discuss neurodiversity, accessibility, and inclusive practices across computer graphics, games, animation, and interactive media. Topics may include communication, collaboration, mentorship, workplace culture, learning environments, executive functioning, and sustainable support strategies. This session also provides an opportunity to discuss ongoing efforts toward building a Neurodiversity Affinity Group within the SIGGRAPH community and fostering year-round connection, advocacy, and visibility.

People

Cheryl Briggs

New 3D creation workflows and international collaboration in the real-time 3D and GenAI Era

Shoko Kimura

Kyoto University

Birds of a Feather

9:00am - 10:00am PDT Wednesday, 22 July 2026 Room 512

Gaming & Interactive

New Technologies

Production & Animation

Animation

Education

Ethics and Society

Fabrication

Generative AI

Industry Insight

Pipeline Tools and Work

Real-Time

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionThis BOF explores how 3D production workflows are evolving across the world and how these changes are reshaping collaboration between studios, toolmakers and creative teams. Topics include interoperability, production organization, real-time 3D and the growing role of generative AI in creative pipelines. Rather than opposing regional approaches, the session will examine shared challenges, emerging practices and opportunities for collaboration. Relevant to the SIGGRAPH community, it addresses workflow design, production technology and AI integration. The session targets studio leaders, production managers, technical directors, CG supervisors, developers, researchers, educators and creators working with modern 3D pipelines.

People

Jean-Christophe Rodier

Technical Paper

Nexus: Native Mesh Generation with Diffusion

10:45am - 10:55am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionNexus is a revolutionary two-stage diffusion framework for generating high-fidelity 3D polygon meshes. By replacing slow sequential modeling with geometry structure and topology diffusion, Nexus effortlessly handles complex, non-manifold geometries and achieves more controllable and faster mesh generation. It delivers significantly superior artistic meshes compared to current state-of-the-art methods.

People

Hanxiao Wang

Institute of Automation, Chinese Academy of Sciences

Xi'an Jiaotong University

Yan-Pei Cao

NILE: Nested Interleaving of Low-Dimensional Elements

Technical Paper

11:15am - 11:25am PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a novel modular modular meta-sampler architecture that bridges local subspace and global sampling, allowing integrator designers to employ specialized low-dimensional samplers while still achieving high-dimensional uniformity.

People

Université Claude Bernard Lyon 1

CNRS - LIRIS

Hui Huang

Shenzhen University

Educator's Forum

No Engine Required: Teaching Game Programming (Mostly) From Scratch

9:00am - 9:20am PDT Tuesday, 21 July 2026 Room 501 ABC

Gaming & Interactive

Research & Education

Education

Games

Image Processing

Modeling

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionThis talk discusses the course philosophy, design, and implementation details of the undergraduate "Video Game Programming" course at the University of Southern California, which has students program both 2D and 3D games largely from scratch.

People

Sanjay Madhav

Matthew Whiting

No-Code Virtual Reality & Immersive Learning

Birds of a Feather

10:00am - 11:00am PDT Thursday, 23 July 2026 Room 510

Research & Education

Animation

Art

Education

Games

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionHow are educators creating immersive learning experiences without coding? This Birds of a Feather session brings together educators, researchers, learning designers, and XR practitioners to share ideas, tools, and workflows for building virtual reality experiences, immersive 360° tours, and digital twins. Participants will discuss successful projects, challenges, and emerging opportunities while exploring platforms that make immersive content creation more accessible than ever. Featuring examples from RMIT University, Australia, this interactive meetup encourages knowledge sharing, networking, and collaboration. Join the conversation, showcase your work, discover new approaches, and help shape the future of immersive education.

People

Keith Hibbert

RMIT University

Technical Paper

Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering

2:20pm - 2:30pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

DescriptionWe present a LOS-guided NLOS imaging pipeline for arbitrary relay surface geometries, representing hidden scenes with 3D Gaussian primitives and developing an efficient differentiable transient renderer. Real experiments on complex relay surfaces captured with our custom system show improved robustness and broaden the practical applicability of NLOS imaging.

People

NPR, Style & Abstraction - Interactive Discussion

Technical Paper

10:00am - 10:30am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

Technical Paper

Numerical Geometry a la Mode - Interactive Discussion

9:40am - 10:05am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Numerical Methods for Geometry Processing - Interactive Discussion

4:45pm - 5:15pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Industry Session

NVIDIA Graphics Developer Tools Roadmap: Agentic AI and Beyond (First Offering)

2:00pm - 2:25pm PDT Sunday, 19 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionThis presentation offers a focused update on the state of NVIDIA's graphics developer tools and a look at how agentic AI workflows are shaping their future direction. Covering recent advances in Nsight Graphics, Nsight Systems, and Nsight Aftermath, the session highlights key improvements to debugging, profiling, and crash analysis capabilities alongside an exploration of where AI-driven automation is heading next.

Attendees will come away with a grounded understanding of the current tooling landscape and practical insight into the agentic AI features being built for graphics developers. This presentation is paired with two hands-on labs where participants will directly use and explore AI-assisted workflows.

People

Industry Session

NVIDIA Graphics Developer Tools Roadmap: Agentic AI and Beyond (Second Offering)

9:00am - 9:25am PDT Monday, 20 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

People

Industry Session

NVIDIA Hands-On Lab: AI-Assisted Graphics Debugging with Nsight Graphics (First Offering)

2:30pm - 4:00pm PDT Sunday, 19 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionModern graphics applications are getting increasingly difficult to debug. Ray Tracing, advanced rendering pipelines with neural rendering, GPU crashes, and performance bottlenecks often require developers to navigate large amounts of data before identifying the true source of a problem. At the same time, AI-powered tools are beginning to transform how developers investigate and understand complex systems.

In this hands-on lab, participants will enter the Hall of Mysteries, an interactive graphics debugging experience built around a series of realistic rendering and performance challenges. Using a preview of the in-development Nsight Graphics MCP (Model Context Protocol) server, participants will study a Vulkan application to investigate visual artifacts, analyze renderer behavior, diagnose GPU crashes, and optimize performance using professional graphics debugging workflows. Rather than following a scripted tutorial or traditional use of the tooling, participants will gather evidence, formulate hypotheses, inspect captures and traces, and verify conclusions through AI-guided investigation. Along the way, they will learn how AI-assisted workflows can accelerate debugging while preserving the reasoning and verification skills required to solve real graphics problems.
By the end, participants will have solved multiple graphics debugging challenges and gained practical experience using AI-assisted workflows to investigate and resolve issues in modern graphics applications.

People

Aurelio Reis

NVIDIA Hands-On Lab: AI-Assisted Graphics Debugging with Nsight Graphics (Second Offering)

Industry Session

9:30am - 11:00am PDT Monday, 20 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

People

Aurelio Reis

NVIDIA Hands-On Lab: AI-Assisted Graphics Profiling with Nsight Systems (First Offering)

Industry Session

4:15pm - 5:15pm PDT Sunday, 19 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionThis training lab offers graphics developers a look at the agentic future being built into Nsight Systems, with a focus on holistic analysis of CPU and GPU performance. Participants will work through hands-on scenarios where AI agents assist with performance analysis . The session bridges the gap between emerging model capabilities and the practical realities of real-time and offline graphics pipelines. Developers at all levels will gain actionable insight into how agentic AI workflows can be adopted today and what innovations are on the horizon.

People

Industry Session

NVIDIA Hands-On Lab: AI-Assisted Graphics Profiling with Nsight Systems (Second Offering)

11:15am - 12:15pm PDT Monday, 20 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

People

Industry Session

NVIDIA Hands-On Lab: Blender, Oranges, and OVRTX (Not Your Typical Smoothie)

1:45pm - 3:15pm PDT Wednesday, 22 July 2026 Room 502B

New Technologies

Research & Education

Generative AI

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionBlender is where many 3D ideas first take shape, and this course in the NVIDIA Physical AI Agent Bootcamp shows how to extend that familiar workspace with Omniverse libraries instead of moving the work somewhere else. Attendees will use AI agents to scaffold a Blender integration that connects ovrtx, ovphysx, and ovstage into a live creative workflow.
The session walks through bringing GPU-accelerated path-traced rendering into Blender’s viewport.. Along the way, attendees will see how Blender’s scene graph can connect to Omniverse-powered rendering and simulation services.
By the end, participants will have an RTX-rendered, physics-enabled scene running inside Blender, plus a clearer model for how composable Omniverse libraries can extend existing tools used by artists, technical directors, and simulation teams.

People

Max Bickley

NVIDIA Hands-On Lab: From Perception to Prediction - Developing Physical AI with Cosmos 3

Industry Session

1:30pm - 3:00pm PDT Monday, 20 July 2026 Room 502B

New Technologies

Research & Education

Generative AI

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionIn this lab, we'll work hands-on across three core capabilities of NVIDIA Cosmos 3: reasoning, world generation, and action prediction. We'll use Cosmos 3 Nano Reasoner to caption real robot video, generate augmentation prompts, and validate synthetic footage using chain-of-thought reasoning. We'll then use Cosmos 3 and Cosmos-Transfer2.5 to synthesize and transform photorealistic video from those prompts, scaling training data without new recording sessions.

Finally, we'll apply Cosmos 3 in different action modes to translate scene understanding into embodied control commands, completing the perceive → reason → act loop.

People

Asawaree Bhide

NVIDIA Hands-On Lab: Isaac Sim and the Fine Art of Making Your Robot Pick Things Up

Industry Session

3:30pm - 5:00pm PDT Wednesday, 22 July 2026 Room 502B

New Technologies

Generative AI

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionThis hands-on course in the NVIDIA Physical AI Agent Bootcamp turns an empty USD stage into a working Isaac Sim robot scene, with AI agents acting as simulation setup partners. Attendees will import a robot manipulator from URDF, compose the scene using prior lab assets or user-selected environments, and bring SimReady content into Isaac for testing.
The session focuses on the practical path from “nothing is in the scene” to “the robot picked up the cube.” Participants will configure the robot, prepare the object, validate physics behavior, tune the scene, and execute a basic pick-and-place task. Agent skills handle repeatable setup steps so attendees can focus on scene intent, simulation checks, and task behavior.
By the end, attendees will have a composed Isaac Sim scene with a physics-validated robot, interactive assets, and a successful pick-and-place task that connects OpenUSD scene building to robotics simulation.

People

Rishabh Chadha

NVIDIA Hands-On Lab: Nsight Graphics in Action: Develop and Debug Modern Ray-Tracing Applications

Industry Session

11:00am - 12:30pm PDT Sunday, 19 July 2026 Room 502B

Gaming & Interactive

Games

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionDive into the world of high-performance graphics programming with this hands-on lab focused on developing and debugging real-time rendering and ray tracing applications built with Vulkan and Direct3D 12. This lab teaches how to effectively use NVIDIA Nsight Graphics to inspect and debug frames to identify and diagnose common rendering bugs and performance blockers.

By the end of the lab participants will understand the direct connection between the tools and the graphics runtime, and will be prepared to use Nsight Graphics with their own applications. Key tools covered include the Graphics Debugger, Ray Tracing Inspector, Shader Debugger, and GPU Crash Dump Inspector.

People

Industry Session

NVIDIA Hands-On Lab: Ray Trace Your Way To A Better Life with Omniverse Libraries, OpenUSD, Agents, and You

9:00am - 10:30am PDT Wednesday, 22 July 2026 Room 502B

New Technologies

Research & Education

Digital Twins

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionWelcome to the first course in the NVIDIA Physical AI Agent Bootcamp.
Physical AI systems need visual worlds that can be rendered, inspected, queried, and trusted before they are used for simulation, robotics testing, or training. This hands-on course introduces that foundation by guiding attendees through building an OpenUSD-based RTX viewport with NVIDIA Omniverse libraries and AI-agent-assisted development.
Starting from a minimal Python renderer, attendees will create an interactive app that loads USD scenes, displays RTX output, exposes camera views, queries scene attributes, and writes image results. They will also learn a repeatable agent workflow: define the goal, provide context, name the relevant skills, review the generated diff, and run only after the code is understood.
By the end, participants will have a working RTX viewport application and a practical method for using AI agents to build reliable graphics and simulation tools for physical AI workflows.

People

Ashley Goldstein

NVIDIA Hands-On Lab: SimReady or Not, Here Comes Gravity with OpenUSD for Simulation

Industry Session

10:45am - 12:15pm PDT Wednesday, 22 July 2026 Room 502B

New Technologies

Research & Education

Generative AI

Physical AI

Pipeline Tools and Work

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionPhysics is at the heart of building reliable physical AI systems, and this course in the NVIDIA Physical AI Agent Bootcamp explores how to move from visual inspection into simulation readiness.

Workflows in physical AI need assets that are structured, validated, and physically meaningful. Building on the prior OpenUSD and RTX viewport lab, this hands-on course moves from visual inspection into simulation readiness.

Attendees will validate OpenUSD assets for simulation-ready (SimReady) workflows, convert CAD and Gaussian splat content to USD, create a physics stage, and assemble environments such as stairs, ramps, or other test layouts. They will enable physics, make scene objects interactable, and run simulations to see how assets behave under gravity and user input.

By the end, attendees will have a runnable physics scene with validated assets, converted USD content, and an interactive environment ready for robotics testing or physical AI workflows.

People

Ashley Goldstein

NVIDIA Physical AI Day | Building Physics-Aware, RTX-Enabled Apps with NVIDIA Omniverse Libraries and AI Agents

Industry Session

2:00pm - 2:50pm PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Artificial Intelligence/Machine Learning

Capture/Scanning

Digital Twins

Physical AI

Real-Time

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin Damien Fagnou for a hands-on look at building physics-aware, RTX-enabled simulation apps with NVIDIA Omniverse libraries. Starting from an existing 3D application, Damien will show how developers can connect OpenUSD scenes, RTX rendering, physics, simulation, and UI capabilities into a working prototype. Lexi, an AI agent co-host, will help show how agents can inspect scenes, call tools, and speed up iteration while Omniverse libraries provide the foundation for repeatable physical AI workflows in 3D graphics and simulation.

People

Damien Fagnou

NVIDIA Physical AI Day | Building SimReady 3D Worlds for Physical AI

Industry Session

10:30am - 11:20am PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Artificial Intelligence/Machine Learning

Capture/Scanning

Digital Twins

Physical AI

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionPhysical AI needs more than realistic 3D graphics. Developers need simulation-ready 3D worlds with the semantics, scale, materials, physics, and validation required for robotics, AI training, and world model development. This session will explore how teams can use SimReady and OpenUSD-based assets to prepare 3D worlds for downstream physical AI workflows.

People

Industry Session

NVIDIA Physical AI Day | Career Growth in Physical AI: Bringing 3D Graphics Skills into Robotics and Digital Twins

1:00pm - 1:50pm PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Artificial Intelligence/Machine Learning

Capture/Scanning

Digital Twins

Physical AI

Real-Time

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionCreative 3D skills are becoming increasingly relevant to physical AI. Join this career growth panel to hear how industry leaders have moved from 3D graphics and content creation into roles across robotics, AI, simulation, and digital twins. Panelists will share what carried over, what they had to learn, and practical advice for others looking to make the same move.

People

Industry Session

NVIDIA Physical AI Day | How to Develop a Real-Time 3D Digital Twin for Rapid Engineering Design

11:30am - 11:50am PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Artificial Intelligence/Machine Learning

Digital Twins

Physical AI

Real-Time

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionLearn how to build a real-time 3D digital twin for rapid engineering design using NVIDIA Omniverse and CUDA-X libraries, AI physics models, and agentic engineering tools. This session will explore how leading simulation providers are leveraging NVIDIA technologies to enable real-time digital twins that accelerate design iteration and improve engineering workflows. We will highlight how Rivian is leveraging Siemens technologies accelerated by NVIDIA and AI physics to achieve rapid automotive design.

People

Abigail Breazeale

NVIDIA Physical AI Day | Introduction to Newton: Open-Source GPU Physics for Robotics

Industry Session

4:00pm - 4:50pm PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Physical AI

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionResearchers and developers need faster, physically grounded simulation to model complex interactions and close the sim-to-real gap across diverse robot embodiments. Newton is an open-source, GPU-accelerated physics engine built on NVIDIA Warp. With OpenUSD integration, Newton enables real-time simulation of rigid and soft bodies, contact, friction, and actuators for advancing robot learning and simulation research

People

Industry Session

NVIDIA Physical AI Day | OpenUSD for AI Agents, Model-Driven Workflows, and 3D Graphics Pipelines

10:00am - 10:20am PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Digital Twins

Graphics Systems Architecture

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionOpenUSD is becoming a foundation for how developers build, connect, and validate 3D graphics pipelines for physical AI. As AI agents and open models begin helping teams create simulation environments, developers need scene data they can direct, inspect, and trust. This session covers how the latest OpenUSD standard work supports modular, interoperable 3D worlds, and how NVIDIA is using OpenUSD across agentic physical AI workflows.

People

Aaron Luk

NVIDIA Physical AI Day | World Models : The Frontier of Physical AI, Unlocked By Graphics

Industry Session

9:00am - 9:50am PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Computer Vision

Generative AI

Physical AI

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionPhysical AI begins with the ability to see, understand, generate, and simulate the world. In this opening address, Ming-Yu Liu will explore why world models are becoming one of AI’s most exciting frontiers, and why 3D graphics is central to the shift. The session will dive into the latest open frontier world model, NVIDIA Cosmos 3, exploring its breakthrough architecture built to accelerate vision reasoning, synthetic data generation, and policy training. Attendees will also learn how generative AI, simulation technologies, and agentic AI are converging to advance physical AI.

People

Ming-Yu Liu

NVIDIA Physical AI Day: Autonomous Vehicle Simulation Technologies with NuRec, 3D Gaussian, Cosmos-Dreams

Industry Session

3:00pm - 3:50pm PDT Tuesday, 21 July 2026 Room 502A

New Technologies

Artificial Intelligence/Machine Learning

Computer Vision

Generative AI

Physical AI

Real-Time

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionLast year generating five seconds of photorealistic simulated driving took minutes of compute. Today, you can interactively drive through a world that has never existed in real time, rendered frame by frame on a single GPU. This talk covers two complementary approaches that make this possible: neural scene reconstruction from real-world captures with NVIDIA Omniverse NuRec and generative scenario synthesis with NVIDIA Cosmos-Dreams. It will cover open problems and solutions in scene representation, temporal consistency, and controllable generation, all core computer graphics challenges.

People

Industry Session

NVIDIA RTX Rendering Day | Advancing LED Virtual Production with Neural Rendering

4:30pm - 5:00pm PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Artificial Intelligence/Machine Learning

Display

Performance

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionAchieving high frame rates and visual fidelity on LED stages requires continuous pipeline innovation. This session explores how NVIDIA DLSS technologies, including Frame Generation, Super Resolution, and Ray Reconstruction, can deliver performance and quality gains for Unreal Engine-based virtual production. Markus Hoell will discuss how real-time AI inference can offload heavy rendering workloads, along with real-world developer stories covering engineering challenges, pipeline hurdles, future DLSS architecture considerations, and lessons learned from adapting neural rendering technologies for LED environments.

People

Markus Hoell

Dimension Studio

Industry Session

NVIDIA RTX Rendering Day | Applied Research for Ray Tracing Massive Scenes in Real Time

9:00am - 9:20am PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Capture/Scanning

Geometry

Graphics Systems Architecture

Hardware

Real-Time

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionRendering massive, dynamic environments in real time requires new approaches to processing and managing geometry on the GPU. This session presents applied research from the NVIDIA Developer Technology team, including real-time massive forest simulation, RTX Mega Geometry for large-scale scene complexity, and Gaussian splatting for novel view synthesis. It also covers new approaches for GPU-accelerated curve and tube rendering, along with engineering best practices for scaling real-time 3D scene rendering with glTF.

People

Industry Session

NVIDIA RTX Rendering Day | Building a GPU Production Renderer with OptiX at Netflix Animation Studios

4:00pm - 4:20pm PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Animation

Graphics Systems Architecture

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionMaintaining real-time interactivity while navigating complex, large-scale animation environments is a major challenge for production pipelines. In this session, Netflix Animation Studios will share its journey building Glimpse, a custom, fully OpenUSD-based ray tracing viewport using NVIDIA OptiX, designed to replace standard viewports such as Maya Viewport 2.0. The presentation will cover how the team addresses large-scale scene complexity, optimizes USD memory sharing, and supports native instancing for large production scenes. Attendees will learn how this high-performance, GPU-accelerated viewport was designed for fast adoption in production workflows.

People

Luke Emrose

Netflix Animation

Industry Session

NVIDIA RTX Rendering Day | Faster Creative Iteration with Autodesk Arnold

11:00am - 11:50am PDT Wednesday, 22 July 2026 Room 502A

New Technologies

Production & Animation

Lighting

Performance

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionCreative iteration remains one of the most expensive challenges in modern content production. In this session, Autodesk will present recent advances in the Academy Award-winning Arnold renderer aimed at reducing technical friction in the creative process. The session will cover architectural improvements to interactive viewport rendering and GPU optimizations that improve responsiveness in complex scenes. Attendees will learn how these advances help artists and technical directors iterate more fluidly while maintaining the robustness, predictability, and image quality expected from a physically based renderer. Autodesk will also share lessons learned from real-world production deployments

People

Sebastien Blaineau-Ortega

NVIDIA RTX Rendering Day | From Pitch to Photorealism: Maxon’s RTX-Powered Solutions for Advertising and Archviz

Industry Session

10:00am - 10:20am PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionSee how Maxon Redshift leverages NVIDIA RTX technology to help advertising, CPG, and architectural visualization teams move from concept pitch to photorealistic results faster. This session covers real-time rendering with RTX and DLSS, along with GPU-accelerated Redshift production workflows in Maxon Cinema 4D and other DCC applications, including Houdini, Maya, and 3ds Max. Attendees will learn how to shorten iteration cycles, enhance visual fidelity, and deliver compelling imagery that wins clients and elevates creative output.

People

Industry Session

NVIDIA RTX Rendering Day | From Viewport to Virtual Production: Real-Time Ray Tracing with Chaos Vantage

9:30am - 9:50am PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionProduction USD assets can now be ray traced interactively as they move from look development into virtual production. This session explores how artists and technical teams can use Chaos Vantage, including NVIDIA DLSS, through its Hydra delegate in SideFX Solaris to render natively assembled OpenUSD scenes and Gaussian splat assets directly in the viewport. Muhammed Hamed will discuss how this pipeline helps bridge the gap between look development and on-set production, with a look at scaling assets into on-set decision-making using Chaos Arena.

People

Muhammed Hamed

Chaos

Industry Session

NVIDIA RTX Rendering Day | GPU Rendering at Film Scale: Karma XPU in Production at Rodeo FX

2:00pm - 2:50pm PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Industry Insight

Lighting

Performance

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionDeploying GPU rendering across large-scale film pipelines requires balancing performance, scalability, and visual fidelity. In this session, SideFX and Rodeo FX will discuss Karma XPU’s capabilities in high-end production rendering. Mark Elendt will provide an overview of Karma XPU’s architecture and its integration of NVIDIA RTX technology, while Julien Héry and Scott Coates will examine practical applications from recent major productions. The session will cover GPU rendering at scale within an OpenUSD-based pipeline, from look development through final frame delivery.

People

Industry Session

NVIDIA RTX Rendering Day | Practical Advances in AI-Accelerated Ray Tracing

1:00pm - 1:50pm PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Geometry

Graphics Systems Architecture

Hardware

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionModern rendering is rapidly evolving through advances in GPU ray tracing and AI-assisted workflows. NVIDIA engineers will share recent OptiX and ray tracing developments shaping interactive and production renderers. Topics include AI-assisted denoising, DLSS integration, curve rendering, debugging and profiling, compile-time workflows, and support for larger, more dynamic, and more programmable rendering systems. The talk also examines evolving areas such as neural rendering, differentiable workflows, Gaussian splats, and memory-scalable scene management, with an emphasis on what is practical today and what is coming next.

People

Industry Session

NVIDIA RTX Rendering Day | Real-Time Stylized Workflows: GPU Accelerated Creativity at ILM

3:00pm - 3:50pm PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Animation

Industry Insight

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionIn the fast paced world of short-form content, traditional rendering bottlenecks can stifle creativity, slow iteration, and limit use across media types. ILM’s Landis Fields and his team break down their real-time production pipeline that leverages GPU-accelerated workflows across each phase. Designed for creatives and technical directors alike, this session will walk through ILM’s process of creating stylized short form content. Everything from designing to executing a high-fidelity project entirely within a real-time ecosystem, drastically reducing render times, enabling live collaborative reviews, and empowering small teams to make creative decisions using a process that would otherwise be cost prohibitive.

People

Landis Fields

ILM/Lucasfilm

Industry Session

NVIDIA RTX Rendering Day | Rendering’s Next Frontier with OTOY

10:30am - 10:50am PDT Wednesday, 22 July 2026 Room 502A

Production & Animation

Artificial Intelligence/Machine Learning

Capture/Scanning

Generative AI

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionEmerging trends in GPU rendering are expanding what’s possible across motion graphics, filmmaking, product design, VFX, games, virtual production, immersive media, and beyond. This session looks at how advances in frontier AI technologies, workflows, and IP provenance tools are influencing the future of rendering. Attendees will gain a forward-looking view of how these trends are shaping creative industries.

People

Jules Urbach

OTOY

Course

NVIDIA: A Step-by-Step Introduction to the ANARI Rendering API

2:00pm - 3:30pm PDT Thursday, 23 July 2026 Room 515 A

Gaming & Interactive

Production & Animation

Research & Education

Graphics Systems Architecture

Rendering

Scientific Visualization

Full Conference Supporter

Full Conference

DescriptionThis course introduces the Khronos ANARI rendering API using a highly practical, step-by-step approach in which attendees learn to write increasingly capable ANARI based applications. At the end of this course, users should be easily able to realize their own 3D applications using ANARI for both interactive and offline rendering use cases.

People

Course

NVIDIA: Advanced Real-Time Volume Graphics

9:00am - 12:15pm PDT Thursday, 23 July 2026 411 Theatre

Production & Animation

Research & Education

Performance

Rendering

Scientific Visualization

Full Conference Supporter

Full Conference

DescriptionThis course teaches attendees how to write sci-vis volume renderers on modern architectures. Since the last course at Eurographics 2006 the hardware and algorithmic landscape have changed tremendously. We show how this has influenced the state-of-the-art in real-time volume graphics in the last years.

People

Stefan Zellmann

University of Cologne

Course

NVIDIA: Beyond 3D: From Real-World Objects to Digital Assets and Physical AI

2:00pm - 5:15pm PDT Sunday, 19 July 2026 Room 403 A

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Capture/Scanning

Digital Twins

Generative AI

Geometry

Physical AI

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionDiscover how scalable compute, advanced graphics and generative AI reshape scientific and cultural narratives. Leveraging AI and neural graphics, we guide attendees through the complete object lifecycle - Seeing, Reconstructing, Restoring, and Simulating. Learn to build active, physically grounded digital twins that unlock deep insights across scientific and cultural domains.

People

Zoe Ryan

NVIDIA: How AI is Changing Education

Educator's Day Session

11:00am - 12:00pm PDT Monday, 20 July 2026 Room 411

Research & Education

Artificial Intelligence/Machine Learning

Education

Industry Insight

Full Conference Supporter

Full Conference

Experience

DescriptionArtificial intelligence is fundamentally reshaping how students learn, how educators teach, and how institutions deliver knowledge at scale. This panel brings together innovators at the forefront of AI-driven education — from Studyfetch, a leading AI-powered study platform transforming how students engage with course material, to NVIDIA's Deep Learning Institute and Community Educator programs, which are equipping the next generation of AI practitioners worldwide.
Panelists will explore the ways AI is fundamentally changing how we teach and learn. Generative AI and large language models are personalizing the learning experience, accelerating skill development, and democratizing access to high-quality education. Discussion will cover real-world deployment of AI tools in academic and professional training environments, the challenges of integrating these technologies responsibly, and what the future classroom looks like as AI capabilities continue to advance.
Attendees will leave with a practical understanding of how AI is being applied in education today, key considerations for educators and institutions adopting these tools, and a clear perspective on where human instruction and AI assistance intersect most powerfully

People

Jacob Liberman

NWON Large-Scale Flexible Electrostatic Speaker for Immersive Spatial Audio

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

Description"Where Sound Meets Tomorrow" presents a revolutionary fabric-integrated speaker system that blends seamless aesthetics with high-fidelity audio. This thin, flexible, and washable textile transforms everyday surfaces and garments into immersive acoustic interfaces, unlocking new possibilities for wearable technology, interior design, and interactive spatial experiences.

People

Akihisa Suzuki

Tsuchiya Co., Ltd.

Manabu Yoshida

National Institute of Advanced Industrial Science and Technology (AIST)

Hitoshi Ito

Tsuchiya TSCO CO., Ltd

Technical Paper

Object-Space Analysis of Local Contrast Sensitivity for Hierarchical Representations of 3D Gaussians

2:10pm - 2:20pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present an object-space contrast sensitivity analysis for 3D Gaussian representations that estimates spatial frequency responses without explicit rasterization using analytical Fourier transforms and the projection-slice theorem. This enables contrast-sensitivity-based perceptual evaluation and efficient foveated rendering via hierarchical Gaussian level selection, preserving visual quality while reducing rendering cost.

People

Naoto Yoshii

Suguru Saito

Masataka Sawayama

Hokkaido University

Yoshinori Dobashi

Hokkaido University

Computer Animation Festival

Games Summit

Ocean Futurisms: Havsrå

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionOcean Futurisms is a collaborative project between TBA21–Academy, Radical Ocean Futures and Inferstudio. Through three original animated short films, the project invites audiences to step into alternative, science-based futures for the ocean. Blending scientific forecasts with immersive storytelling, each of the films rehearses questions for the future of ocean policy/governance through speculative scenario making and worldbuilding. These films act as simulated visions of worlds that might yet be…for better, or for worse.

In Havsrå, a direct action activist organisation mobilises a global audience by live-streaming their operations as they attempt to disrupt illegal deep sea mining.

Designed for use in workshops and educational screenings with ocean scientists and policymakers, the Ocean Futurisms films are an ambitious experiment in the power of narrative to inspire real-world conversations about the radical and urgent changes required to safeguard Earth's oceans for the future.

People

Nathan Su

Creative Direction, Production Design, Animation

Bethany Edgoose

Creative Direction, Writing, Editing

Sarah Su

Creative Direction, Sound Design, Music Composition

Computer Animation Festival

Ocean Futurisms: MANA

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionOcean Futurisms is a collaborative project between TBA21–Academy, Radical Ocean Futures and Inferstudio. Through three original animated short films, the project invites audiences to step into alternative, science-based futures for the ocean. Blending scientific forecasts with immersive storytelling, each of the films rehearses questions for the future of ocean policy/governance through speculative scenario making and worldbuilding. These films act as simulated visions of worlds that might yet be…for better, or for worse.

In this first film of the project, M.A.N.A, we follow a future ocean noise pollution data analyst - working within an alliance of island states redefining ocean governance amidst the realities of climate crisis.

Designed for use in workshops and educational screenings with ocean scientists and policymakers, the Ocean Futurisms films are an ambitious experiment in the power of narrative to inspire real-world conversations about the radical and urgent changes required to safeguard Earth's oceans for the future.

People

Bethany Edgoose

Creative Direction, Writing, Editing

Nathan Su

Creative Direction, Production Design, Animation

Sarah Su

Creative Direction, Sound Design, Music Composition

Olaf: Bringing an Animated Character to Life in the Physical World

Real-Time Live!

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionWe brought the animated character Olaf to life in the physical world using reinforcement learning and innovative custom hardware. To mirror the animation, we utilized novel rewards to reduce impact noises and prevent actuator overheating. The result is a physically robust robot that authentically captures the character’s stylized motion.

People

OMBI: Open Standards for the Metaverse Browser

Birds of a Feather

1:00pm - 2:30pm PDT Tuesday, 21 July 2026 Room 513

New Technologies

Augmented Reality

Digital Twins

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionAR glasses are arriving. Airports, hospitals, logistics centers, and universities are already planning spatial deployments, but the open infrastructure layer that makes it all work doesn't exist yet. The Open Metaverse Browser Initiative (OMBI), a Metaverse Standards Forum initiative seeded by RP1's operational prototype, is building that layer: an open-source Metaverse Browser Engine (Sneeze) that connects any device to spatial services on demand, on open standards from Khronos, W3C, and OGC, with no proprietary lock-in. This BOF brings together industry contributors to walk through the architecture, share progress, and ensure the AR hardware race produces a genuinely open spatial web.

People

Neil Trevett

Dean Abramson

RP1

Yinch Yeap

RP1

OmniHands: Robust Motion Capture of Interactive Hands via A Versatile Transformer

Technical Paper

4:35pm - 4:45pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionOmniHands is a universal architecture for hand reconstruction across diverse scenarios, supporting single-hand reconstruction, two-hand interaction reconstruction, temporal inputs, and multi-view inputs. It achieves this within a unified framework by first tokenizing the features of each hand and then fusing the tokens in a task-dependent manner

People

Dixuan Lin

Beijing Normal University

Beijing Normal University

Dixuan Lin

Beijing Normal University, Stanford University

Technical Paper

OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation

2:10pm - 2:20pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Rendering

Full Conference Supporter

Full Conference

DescriptionThis work introduces a controllable panoramic video generation framework designed for long-horizon scene wandering. It utilizes a global-to-local preview-and-refine pipeline to synthesize high-fidelity, spatially and temporally coherent panoramic videos from a single input panoramic image or video.

People

Yuheng Liu

Xin Lin

Xinke Li

Baihan Yang

Chen Wang

Kalyan Sunkavalli

Yannick Hold-Geoffroy

On-Set Image-Based Asset Acquisition at LAIKA: The Interface Between Practical and Digital in Hybrid Filmmaking

Talks

4:05pm - 4:25pm PDT Sunday, 19 July 2026 Room 403 B

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Games

Geometry

Hardware

Image Processing

Performance

Pipeline Tools and Work

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionLAIKA’s VFX look development artists create both digital doubles and CG assets that integrate into the artisan-made world of stop motion film. Our tools for on-set visual data acquisition drive look development, validate the congruity of the asset, and produce shot ready assets that fit LAIKA’s bespoke, handmade vision.

People

Technical Paper

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

9:00am - 9:10am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Modeling

Full Conference Supporter

Full Conference

DescriptionModern T2I DiTs are powerful yet often lack diversity. We identify a novel intervention point within DiTs: the Contextual Space at the transformer block level, where textual tokens are enriched by image content. We propose a method that repels a batch of samples in this space to produce diverse generations.

People

Computer Animation Festival

Oniko

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionOniko is a dark, stylised animated short set in Edo-period Japan, where a princess is forced to flee her snowbound castle with her newborn as samurai hunt her through the night. Driven into a storm-lashed forest and toward a cliff above the ocean, she must rely on determination, sacrifice, and a terrifying secret bound to her child to survive. Blending historical drama with supernatural myth, Oniko is a tense, atmospheric tale about motherhood, defiance, and the cost of choosing one’s own fate.

People

Creative Lead

CG Lead (FX)

CG Lead (3D)

Birds of a Feather

Open Review Initiative, including OpenRV and xSTUDIO

12:00pm - 1:30pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 3

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionUpdates from the Open Review Initiative team. Demonstration of the latest work in live collaboration protocols including support for annotations. Progress and community updates from OpenRV and xSTUDIO, as well as our work on Encoding, and Plugin Development.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Erik Strauss

Sohonet

Birds of a Feather

OpenColorIO

4:00pm - 5:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionOCIO is an open source color management solution hosted at the Academy Software Foundation. Join us for an informal community discussion around current/planned OCIO development, implementation, and workflows.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Carol Payne

Academy of Motion Picture Arts and Sciences

Opening the door to the neighborhood

Birds of a Feather

OpenEXR

10:00am - 11:00am PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionOpen discussion with project maintainers about new features and future directions.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Kimball Thurston

Weta Digital VFX

Computer Animation Festival

12:30pm - 1:30pm PDT Wednesday, 22 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionThree neighbors—Eunwoo, a new resident; Bumsaeng, living a quiet senior life; and Jisu, worn out by her routine—seemed to have no reason to connect. Yet, they each open a "door," slowly weaving themselves into one another's worlds.

People

Jonghoon Lee

Director

VCRWORKS

Birds of a Feather

OpenTimelineIO

1:00pm - 2:00pm PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 4

Production & Animation

Full Conference Supporter

Full Conference

Experience

DescriptionOpenTimelineIO is an interchange format and API for editorial timeline information. Please join us for an overview of what OpenTimelineIO does and some updates from the past year.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Erik Reinecke

Netflix

Stage Session

OpenUSD streamed to any device, anywhere.

11:30am - 12:00pm PDT Wednesday, 22 July 2026 West Hall A

New Technologies

Artificial Intelligence/Machine Learning

Digital Twins

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionFully path-traced, OpenPBR-compliant OpenUSD, streamed to any consumer device, anywhere.

Reaching low-powered hardware has always meant reducing fidelity, downgrading geometry and texture sizes. That is exactly where photorealism dies. Miris doesn't work that way. We use AI to condition each 3D asset once upstream, optimizing across devices, network conditions, and content characteristics, then stream it adaptively to any device. Our radiance field technology, built leveraging NVIDIA fVDB software and CoreWeave infrastructure enables Miris to deliver high-fidelity content at global scale.

Join Sean Looper, CTO of Miris, for a look at how the pipeline is built and how Playbook, Evercast, CGAxis, and Voxel51 are putting it to work across digital twins, physical AI, media and entertainment, and digital asset marketplaces.

If you build with 3D, come talk shop. We are looking for partners.

People

Sean Looper

Miris

Birds of a Feather

OpenVDB

10:00am - 11:00am PDT Monday, 20 July 2026 JW Marriott - Gold Ballroom 3

Production & Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionSignificant changes in the upcoming major release of OpenVDB.

This BoF is part of a full day of open source BoFs hosted by the Academy Software Foundation as part of Open Source Days. Learn more at opensourcedays.aswf.io.

People

Ken Museth

OpenXR: From XR Portability to Spatial Computing Platform

Birds of a Feather

2:00pm - 3:30pm PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Artificial Intelligence/Machine Learning

Digital Twins

Generative AI

Graphics Systems Architecture

Hardware

Industry Insight

Performance

Real-Time

Rendering

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionJoin the Khronos Group, industry leaders, and the OpenXR community for an interactive session exploring how OpenXR is evolving beyond device interoperability to help power the next generation of intelligent, context aware spatial experiences. We will cover the Spatial Entity Framework, new spatial extensions, OpenXR 1.1, and the expanded Extension Matrix, now including middleware support visibility across Unity, Unreal, Godot, and more. Plus best practices for shipping across headsets, AR glasses, Android XR, mobile, and edge deployments. Bring your questions, share your perspective, and help shape what comes next for OpenXR.

People

Course

Optimal Transport for Fluid Simulation: New and Old

9:00am - 12:15pm PDT Sunday, 19 July 2026 Room 408 B

Research & Education

Geometry

Math Foundations and Theory

Simulation

Full Conference Supporter

Full Conference

DescriptionThis course on Fluid Simulation focuses on Optimal Transport, a mathematical toolbox for creating a 3D mesh representation that follows the movement of the fluid while accurately ensuring volume conservation, fluid-boundary interactions and free-surface evolution. For a hands-on experience, it includes many bring-back-home programming examples, from simple to elaborate.

People

Bruno Lévy

Institut national de recherche en informatique et en automatique (INRIA)

Cyprien Plateau--Holleville

Institut national de recherche en informatique et en automatique (INRIA)

Course

Orchestrating Multimodal Control for Unified Audio-Visual Synthesis

3:45pm - 5:15pm PDT Tuesday, 21 July 2026 Room 408 A

New Technologies

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Digital Twins

Generative AI

Rendering

Full Conference Supporter

Full Conference

DescriptionThis course introduces a unified paradigm for multimodal control of joint audio-visual synthesis using the LTX-2 foundation model. Beyond text prompts, we demonstrate precise control via audio, video, imagery, and spatial data. Attendees will learn dual-stream transformer architectural innovations and practical techniques for orchestrating high-fidelity, aligned multimodal generation

People

Computer Animation Festival

Orchid Square

12:30pm - 1:30pm PDT Thursday, 23 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionDuring the Hungry Ghost Festival in Hong Kong, 18 year old Jane is on a night out with her friends. When she spots her six year old sister in the busy crowd, she starts a frantic search through the party district that will bring her to face the ghosts of her repressed past.

People

Director

Director

Director

Director

Director

Eléonore Hattenberger

Director

Director

Director

Director

Spatial Storytelling

OUT OF THE ASHES: A Work-In-Progress Spatial Story of the Human Cost of Climate Change

2:00pm - 2:45pm PDT Monday, 20 July 2026 Concourse Hall

Gaming & Interactive

New Technologies

Capture/Scanning

Digital Twins

Generative AI

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionOUT OF THE ASHES co-directors Nonny de la Peña and Rory Mitchell detail the process of creating the work-in-progress immersive documentary beginning with 3D scanning the devastation in the aftermath of the Los Angeles Fires of 2025 through the conception and execution of 3DGS & 4DGS pipelines for Unity.

People

Nonny de la Peña PhD

PAColorHolo: A Perceptually-Aware Color Management Framework for Holographic Displays

Emblematic Group

Rory Mitchell

MERCANTILE

Technical Paper

10:55am - 11:05am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present PAColorHolo, a perceptually-aware color management framework that enables accurate color reproduction in holographic displays. Our approach jointly addresses system-level color distortions through color space transformation, adaptive illumination control, and a color-restoration neural network. Simulations, optical experiments, and a user study demonstrate improved perceptual color fidelity.

People

Chun Chen

Minseok Chae

Seung-Woo Nam

Myeong-Ho Choi

Minseong Kim

Eunbi Lee

Yoonchan Jeong

Jae-Hyeung Park

Chun Chen

Myeong-Ho Choi

Parametric Surfaces - Interactive Discussion

Technical Paper

3:00pm - 3:30pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Talks

Pashboard: Modernizing Rez for Animation

4:45pm - 5:05pm PDT Thursday, 23 July 2026 Room 408 A

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Graphics Systems Architecture

Image Processing

Lighting

Performance

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionNetflix Animation Studios presents Pashboard, a cloud-native evolution of the Rez package manager. By integrating with Netflix’s streaming infrastructure and zero-trust security, Pashboard solves the latency and access hurdles of traditional on-premise pipelines. This novel system enables a high-performance, globally distributed software workflow for artists and developers across six continents.

People

Ryan Bland

Jacob Melvin

Chethna Kabeerdoss

Path Guiding in Disney's "Zootopia 2"

Talks

10:45am - 11:05am PDT Thursday, 23 July 2026 Room 515 A

Arts & Design

Production & Animation

Research & Education

Animation

Augmented Reality

Dynamics

Games

Geometry

Lighting

Math Foundations and Theory

Modeling

Pipeline Tools and Work

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWalt Disney Animation Studios' “Zootopia 2” was the first film to adopt Disney's Hyperion Renderer's second-generation path guiding system. Building on lessons we previously shared in “Path Guiding in Production and Recent Advancements”, this talk presents new advancements of our system that enabled large-scale adoption, improving workflows and rendering efficiency.

People

Yining Karl Li

Lea Reichardt

Marco Manzi

Alexander Rath

Brian Green

Neelima Karanam

PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments

Technical Paper

2:10pm - 2:20pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present PatternGSL, a structured and template-free representation for simulation-ready 3D garments. Given a single garment image, our VLM-based method predicts editable sewing patterns with explicit panel, edge, and stitch topology. Trained on the large-scale PatternGSLData dataset, it enables accurate reconstruction, cloth simulation, and downstream garment design workflows.

People

Zhenyang Li

Tsinghua University, China

Lutao Jiang

The Hong Kong University of Science and Technology (Guangzhou)

Yizhou Zhao

Weikai Chen

The Hong Kong University of Science and Technology (Guangzhou)

Ying-Cong Chen

Xin Wang

PEGAsus: 3D Personalization of Geometry and Appearance

Technical Paper

11:15am - 11:25am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionPEGAsus enables personalized 3D shape generation by learning reusable geometry and appearance concepts from a single reference shape, supporting both global and region-wise personalization. The learned concepts can be combined with text to synthesize novel personalized 3D assets outperforming existing state-of-the-art solutions.

People

Jingyu Hu

Bin Hu

Ka-Hei Hui

Autodesk Research

Haipeng Li

Perception - Interactive Discussion

Technical Paper

4:55pm - 5:25pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

Art Paper

Perception and Presence - Q&A

10:20am - 10:30am PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Research & Education

Animation

Art

Audio

Augmented Reality

Capture/Scanning

Dynamics

Hardware

Lighting

Performance

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAfter all the presentations, attendees are invited to participate in a Q&A.

Games Summit

Performance Capture at Scale: Building a Pipeline for Battlefield 6 Cinematics

1:45pm - 2:15pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Production & Animation

Games

Full Conference Supporter

Full Conference

Experience

DescriptionFilm-grade virtual production workflows are increasingly finding their way onto game MoCap stages — but adapting them to the pace, scale, and constraints of AAA production is its own challenge. This talk details how EA Create Capture met that challenge for Battlefield 6: from 1-to-1 physical set construction and moving vehicle builds to real-time visualization that enabled key creative decisions on set and same-day editorial delivery.

People

Technical Workshop

Performance, Rendering, and Interaction for Competitive Esports (PRICE)

2:00pm - 5:15pm PDT Thursday, 23 July 2026 Room 406 AB

Gaming & Interactive

Research & Education

Artificial Intelligence/Machine Learning

Display

Games

Graphics Systems Architecture

Hardware

Performance

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThe Performance, Rendering, and Interaction for Competitive Esports (PRICE) workshop brings together cutting-edge research on topics essential to esports, including graphics and rendering, systems and performance, human factors and HCI, computer supported cooperative work (CSCW), data, and artificial intelligence.

Esports is no longer a niche hobby; it is a major cultural and economic force, with a global audience in the hundreds of millions and a market size exceeding $1 billion. The performance and experience of both players and spectators are critically dependent on the underlying technology. Success in competitive games hinges on a complex interplay between hardware capabilities, software optimizations, and the limits of human perception, performance, and experience.

The program includes a keynote, sketch presentations, and interactive panel discussions among sketch authors where the audience will be able to participate in the discussion. Additionally, a few short breaks in the agenda will allow for small group and one-on-one interactions.

Technical Workshop Sketches:

AI Level of Detail: Distance-Aware ML Model Precision Selection for Real-Time Human Motion Prediction in Games
Mathew Varghese, University of Washington

Towards Field Experiments in Esports Competition
Arjun Madhusudan, North Carolina State University
Josef Spjut, Ben Boudaoud, Joohwan Kim, NVIDIA
Benjamin Watson, North Carolina State University

Understanding Emergent Non-Verbal Communication in the Delta Force Competitive Video Game through Multimodal AI Analysis
Jinyuan Guo, Duke Kunshan University
Josef Spjut, NVIDIA

Improving Interaction by Transforming the Render-Display Pipeline
Aaron Fulmer, Francis Marion University; North Carolina State University
Evan Jonson, North Carolina State University
Hee-Jin Choi, Sejong University
Hyoungsik Nam, Kyung Hee University
Benjamin Watson, North Carolina State University

What Do Competitive Players Do With Their Settings? A Multi-Game Esports Configuration Survey
Ashish Rajpurohit, Arjun Madhusudan, Benjamin Watson, North Carolina State University

People

Queensland University of Technology

Madison Klarkowski

Rulon Raymond

Infinity Ward

Mark Claypool

Worcester Polytechnic Institute

Paul Ritaldato

Epic Games

Technical Paper

Persistence-guided Prescribed Topological Simplification

4:25pm - 4:35pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe developed a new algorithm to simplify the topology of a 3D shape to user-prescribed numbers of connected components, handles, and voids, while minimizing geometric changes.

People

Linxuan Rong

Washington University in St. Louis

Tao Ju

Washington University in St. Louis

Technical Paper

Phased & Viscous Fluiids - Interactive Discussion

11:45am - 12:15pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Photons × Force: Differentiable Radiation Pressure Modeling

2:40pm - 2:50pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a system for optimizing spacecraft designs under radiation pressure, the force that photons exert on objects. It combines a fast Monte Carlo simulation, a neural proxy of it, and gradient-based optimization to find spacecraft geometry, or operational parameters that minimize travel time or maximize proximity to a target.

People

Charles Constant

Santosh Bhattarai

Elizabeth Bates

Alan Turing Institute

Marek Ziebart

Tobias Ritschel

Physics Is Easier Than You Think: From Classical to Neural Elastic Simulation

Course

2:00pm - 5:15pm PDT Thursday, 23 July 2026 Petree D

Arts & Design

Gaming & Interactive

Research & Education

Animation

Artificial Intelligence/Machine Learning

Dynamics

Full Conference Supporter

Full Conference

DescriptionThrough theory and reference code, attendees will learn the simple foundations of elastic simulation. Once the basics are established, the course further explores through the current research landscape of neural physics simulation, showing how newcomers can integrate modern physics simulation into their projects.

People

Davide Corigliano

PhD student at ETH Zurich

Otman Benchekroun

Jernej Barbič

Physics-Inspired Procedural Texturing of Extremely Deformable Surfaces

Technical Paper

11:35am - 11:45am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionApplying texture maps to dynamic deformable surfaces presents a significant challenge, due to ever-shifting differences in length scales involved.
We present two novel wave-based procedural texturing algorithms which reproduce common physical properties like advection and self-similarity, enabling physics-guided animation of deforming objects with extreme texture map distortions.

People

Aleksei Kalinov

Mickaël Ly

Christian Hafner

Chris Wojtan

Pinlight AR Near-Eye Display with Large FOV and Expanded Eyebox through Eye Tracking

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe present a compact pinlight AR display that achieves a wide field of view and expanded eyebox via dynamic eye tracking. A camera rig captures multi-view pupil images to estimate 3D pupil position using a neural network, enabling more precise 3D eye tracking. A prototype validates the proposed approach.

People

Zheye Yu

Shanghai University

Shenghao Zhao

SHU General Intelligent Robotics Research Institute

Andrei State

University of North Carolina Chapel Hill

Tat-Jen Cham

Frank Guan

University of North Carolina Chapel Hill

Henry Fuchs

ACM SIGGRAPH 365

Pioneers Featured Speaker - Don Greenberg

10:00am - 11:00am PDT Tuesday, 21 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Education

Ethics and Society

Games

Generative AI

Graphics Systems Architecture

Industry Insight

Pioneers

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionComputer Graphics legend Don Greenberg is the ACM/SIGGRAPH Pioneers Featured Speaker for 2026! Greenberg's astonishingly multi-disciplinary career started in architecture, and has spanned the computer graphics revolution from its genesis in the 1960s. He has taught in the fields of architecture, engineering and computer science, while also being an elite athlete and life-long advisor to the tennis and soccer teams at Cornell. Greenberg’s teaching has covered computer-aided design in architecture as well as computer animation in the Department of Art, and he has simultaneously taught courses in computer science and technology strategy. Greenberg received the 1987 ACM SIGGRAPH Steven A. Coons Award for Outstanding Creative Contributions to Computer Graphics, its highest honor, and the 1989 NCGA Academic Award, the highest educational award given by the National Computer Graphics Association. He is a member of the National Academy of Engineering; Founding Fellow, American Institute of Medical and Biological Engineering; Fellow, Association for Computer Machinery; Fellow, American Association for the Advancement of Science; and the founding director of the 11-year National Science and Technology Center for Computer Graphics and Scientific Visualization.

Don will be sharing his thoughts on THE FUTURE OF SIGGRAPH, in what is sure to be one of the most memorable, pivotal and inspirational keynote conversations in our organization's history. You do not want to miss this!

Please note: Due to a format change, this session will be delivered via live stream for the onsite audience. The talk will be followed by a moderated Q&A.

People

Edward Kramer

ACM/SIGGRAPH Pioneers

Don Greenberg

Cornell University

Technical Paper

Pixal3D: Pixel-Aligned 3D Generation from Images

11:05am - 11:15am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionPixal3D is a pixel-aligned paradigm that solves the fidelity bottleneck in image-to-3D synthesis. By utilizing a back-projection conditioning scheme to explicitly lift 2D features into view-aligned 3D volumes, it eliminates ambiguity, enabling scalable generative reconstruction of highly accurate 3D assets and scenes from single or multi-view images.

People

Victoria University of Wellington

Technical Paper

Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction

2:10pm - 2:20pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Lighting

Full Conference Supporter

Full Conference

DescriptionPixel Cube is a novel lighting system for realistic lighting emulation and high-speed video relighting data acquisition. With a high-quality lighting-aware dataset, we train a diffusion model for dynamic portrait relighting. Our model produces photorealistic, temporally consistent portrait videos under new lighting conditions that faithfully preserve the subject's facial features.

People

Yufan Zhang

Yu Ji

LightThought LLC

Ayo Ajiboye

Rundi Wu

Columbia University

Yu Guo

Changxi Zheng

Columbia University

Jinwei Ye

Pixels2Peaks: Converting Terrain Images to Heightmaps

Technical Paper

11:15am - 11:25am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionPixels2Peaks automates the creation of 3D bare-earth terrain heightmaps from a single 2D photograph. Our method first estimates camera parameters and visible geometry; then uses a guided diffusion model to plausibly synthesize occluded regions. The result maintains geomorphological, hydrological, and view consistencies.

People

Aryamaan Jain

INRIA, Université Côte d'Azur

James Gain

University of Cape Town

Guillaume Cordonnier

INRIA, Université Côte d'Azur

Technical Paper

PixTex: Consistent 3D Texturing via Pixel-Space Multi-View Diffusion

9:40am - 9:50am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

DescriptionWe propose PixTex, the first pixel-space multi-view diffusion framework for texture generation. By bypassing latent compression and utilizing a coarse-to-fine strategy, it ensures lossless geometric guidance and superior pixel-level multi-view consistency, achieving state-of-the-art, high-fidelity, and seamless results.

People

Yuqing Zhang

State Key Lab of CAD&CG, Zhejiang

Yan-Pei Cao

Hao Xu

Yiqian Wu

Sirui Lin

Yuqing Wang

State Key Laboratory of CAD&CG, Zhejiang University

Talks

Playable Music at Runtime: Building a Stateful Audio System for Astral Planes

9:00am - 9:20am PDT Sunday, 19 July 2026 Room 403 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Digital Twins

Education

Fabrication

Games

Generative AI

Geometry

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionAstral Planes replaced loop-based playback with a Unity-native runtime music system where gameplay reshapes composition directly. This production case study explains tracks, bins, notes, shared timing, persistent loops, and how audio architecture changes when composition becomes part of interaction.

People

Clay Ewing

University of Miami

Technical Paper

PointLLM-R: Enhancing 3D Point Cloud Reasoning via Chain-of-Thought

3:45pm - 3:55pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Games

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionPointLLM-R introduces chain-of-thought reasoning for 3D point cloud understanding via a data-centric pipeline. It builds a large reasoning dataset (PoCoTI) and trains a multimodal model that achieves state-of-the-art performance, improving accuracy, interpretability, and robustness across synthetic and real-world 3D tasks.

People

Technical Paper

Points as Tori: Fast Pointwise Signed Distance for Point Clouds

3:45pm - 3:55pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionSigned distance computation has been either fast or robust, but not both. We explain why, using a theory that unifies signed distance with reconstruction. Our method directly estimates signed distance from point clouds, providing fast pointwise evaluation at arbitrary spatial resolution, without requiring discretization, global optimization, or explicit reconstruction.

People

Nicole Feng

Ioannis Gkioulekas

Keenan Crane

Poisson Problems in Computer Graphics

Roblox Research

Course

9:00am - 12:15pm PDT Wednesday, 22 July 2026 Room 515 A

Research & Education

Animation

Dynamics

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionLike a semester long graduate seminar on Poisson Problems in Computer Graphics, this course looks at Poisson problems through the lens of 13 technical papers selected by the lecturers. The lecturers will highlight trends, similarities, differences, and historical threads through the papers.

People

Adam Bargteil

University Of Maryland, Baltimore County

Marc Olano

University Of Maryland, Baltimore County

Technical Paper

Policy-based Foveated Imaging and Perception

2:50pm - 3:00pm PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Full Conference Supporter

Full Conference

DescriptionUltra-high-resolution sensors capture fine details critical for visual perception, but acquiring all pixels at full resolution is often infeasible under realistic constraints. We introduce a real-time, task-aware foveated imaging framework that learns a sensor attention policy to dynamically allocate pixel bandwidth, extensively validated in simulation and on a 200-megapixel prototype.

People

Technical Paper

PQ-Free HD: Priority-Queue-Free Hausdorff Distance for Triangle Meshes on GPU

2:30pm - 2:40pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a method for computing error-bounded Hausdorff distance between triangle meshes on the GPU. By eliminating the serial bottleneck in traditional branch-and-bound algorithms, our approach achieves high-throughput performance and enables geometry processing applications that require guaranteed error control.

People

Zhihao Hu

Renjie Chen

PR-Cage: Progressive Feasibility Relaxation for Tight Bounding Cage Generation

Technical Paper

11:25am - 11:35am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionPR-Cage is an automated framework for generating high-quality cages—simplified mesh proxies that tightly enclose complex geometry. Using a staircase relaxation of a thickness parameter and constrained QEM optimization, it achieves extreme simplification while preserving shape fidelity, enabling efficient contact simulation, deformation, and other graphics applications.

People

Huibiao Wen

University of Health and Rehabilitation Sciences

Kaikai Qin

Shandong Huayun Technology Co., Ltd.

Xinxin Su

Jingcheng Mei

HoteamSoft

Shuangmin Chen

Qingdao University of Science and Technology

Shandong Key Laboratory of Deep Sea Equipment Intelligent Networking

Chongyang Deng

Practical Methods for Kinky-Coily Hair in Animation Production

Talks

9:20am - 9:40am PDT Thursday, 23 July 2026 Room 515 A

New Technologies

Production & Animation

Animation

Dynamics

Geometry

Industry Insight

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionThe talk presents fast, modular approximations of Curly‑Cue’s methods for kinky‑coily hair—switchbacks, phase locking, and period skipping—integrated into Netflix Animation Studio’s Houdini-based grooming pipeline, prioritizing artistic control, simplicity, and interactivity over strict physical accuracy while achieving natural-looking hairstyles.

People

Michael Davison

Guillaume Pernin

Curtis Andrus

Prana Labs | Tripo AI x Prana Labs x NUS

Stage Session

10:30am - 11:00am PDT Wednesday, 22 July 2026 West Hall A

New Technologies

Artificial Intelligence/Machine Learning

Generative AI

Physical AI

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionThis demo is a collaboration between Tripo and Prana that pairs generative 3D content with physically grounded simulation for robot manipulation. Tripo generates the functional 3D assets and drives the generative rendering, producing convincing scenes equipped with simulation-ready geometry. Prana's simulation engine, FLASH, governs the physics of these environments, so contact, grasping, and object dynamics behave in a physically consistent way rather than only looking correct.
Scenarios center on robotic manipulation, such as a robot arm picking up and handling everyday objects. Every interaction is resolved by the simulator, so the same scene that looks real also responds correctly when a gripper makes contact, including objects made of composite materials that combine rigid and flexible parts within a single body. The simulator is fully differentiable, so its physical behavior can be fit to real observations rather than tuned by hand.
Functional 3D generation and physical accuracy are distinct but complementary problems. Tripo's generation provides the precise 3D structure and visual diversity to generalize; Prana's physically grounded simulation makes it behave right with the accuracy contact demands. Together they produce environments both visually rich and physically valid, which is what embodied tasks like grasping require.
We hope to prompt discussion on how generative content and differentiable simulation can build interactive, physically accurate virtual worlds.

People

Talks

Predator: Badlands – The Hunt for Emotions

3:45pm - 4:05pm PDT Wednesday, 22 July 2026 Room 515 A

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Performance

Full Conference Supporter

Full Conference

DescriptionFor Predator: Badlands, Wētā FX VFX Supervisor Sheldon Stopsack and Animation Supervisor Karl Rapley present how they developed Dek, a fully digital facial performance anchored in a practical on-set suit, to sustain a nuanced emotional arc without compromising the Predator’s franchise-defining silhouette and ferocity.

People

Educator's Day Session

Preparing Students for Creative Careers: Teaching the Tools and Workflows the Industry Uses

10:15am - 10:45am PDT Monday, 20 July 2026 Room 411

Gaming & Interactive

Production & Animation

Animation

Digital Twins

Education

Games

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionCreative talent opens the door, but it is hands-on experience with professional tools and production workflows that prepares students for successful careers.

Join Steve Forde, Chief Product Officer at Maxon, as he explores how educators can better align teaching with the realities of today's creative industries. Drawing on examples from film, broadcast, motion graphics, visual effects, and game development, Steve will discuss the technologies and collaborative workflows used by studios around the world, and why experience with industry-standard tools continues to be an important advantage for graduates entering the workforce.

The session will also introduce Maxon's growing education initiatives designed to help educators bring students closer to professional practice. These include classroom support from Maxon's Solutions Experts through guest lectures, masterclasses, and curriculum guidance, along with a new skills assessment tool that enables students to measure their progress and build confidence as they develop practical production skills.

Rather than focusing on software features alone, this session looks at how educators can bridge the gap between classroom learning and professional production, giving students the experience, confidence, and industry relevance they need to succeed in creative careers.

People

Steve Forde

Maxon Computer Inc

Educator's Day Session

Preparing Students for Real-Time: The Hidden Production Shift in 3D Animation

1:00pm - 1:30pm PDT Monday, 20 July 2026 Room 411

Gaming & Interactive

Production & Animation

Research & Education

Animation

Education

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionThe animation industry is shifting, and real-time technology is at the center. But the biggest change isn't purely technical; it's how teams collaborate, make decisions, and move from concept to final shot. This session draws on real studio case studies to reveal the production mindset behind real-time animation in Unreal Engine: collapsed silos, new collaborative workflows, and what that means for classroom learning, curriculum, and the skills students need to succeed.

People

Jamie Hurcomb

Epic Games

Technical Paper

Preventing Collision - Interactive Discussion

10:00am - 10:30am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Geometry

Hardware

Modeling

Simulation

Full Conference Supporter

Full Conference

Art Paper

Printing the Underdetermined: Materializing Multi-solutionness in Figurative Paintings

5:25pm - 5:45pm PDT Wednesday, 22 July 2026 411 Theatre

Arts & Design

New Technologies

Production & Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Display

Education

Fabrication

Generative AI

Geometry

Hardware

Image Processing

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Robotics

Full Conference Supporter

Full Conference

Experience

DescriptionAs generative models enter graphics pipelines, we need ways to see what gets assumed, invented, or discarded when an image becomes a 3D scene. Figurative paintings are a clear test case. Our workflow keeps this non-uniqueness explicit by sampling plausible completions, reconstructing each via 3D Gaussian Splatting, and fabricating them with volumetric 3D Printing. These artifacts expose where evidence constrains geometry and where it doesn't, opening a shared language for uncertainty across art and graphics.

People

Yutao Ming

Teng Xu

Youjia Wang

Yunyang Liu

Fengmin Yang

Fuqiang Zhao

Yanjun Zhou

Probe-based Walk on Spheres for Efficient Path Reusing

Technical Paper

3:45pm - 3:55pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionA Walk on Spheres-based Monte Carlo PDE solver that reuses full random walk paths via fixed probes, achieving lower variance and faster convergence on mixed-boundary Laplace, Poisson, and screened Poisson problems.

People

Wanchao Huang

Yutian Zhu

Qing Fang

Production-Driven Data Management for a Service-Based Pipeline

Talks

10:00am - 10:20am PDT Sunday, 19 July 2026 Petree D

Production & Animation

Animation

Pipeline Tools and Work

Real-Time

Full Conference Supporter

Full Conference

DescriptionWalt Disney Animation Studios Technology developed a new automated data management system that migrates production resources between storage tiers and cleans up unneeded data throughout a film’s lifetime. The system ensures no disruption to end users and maintains data integrity while also aiming to be user-friendly, scalable, and observable.

People

Katie Vinson

Yaash Jain

Oliver Staeubli

Timothy Hoff

Production-Ready Camera Tracking via LiDAR-Constrained Deep Optical Flow

Talks

3:45pm - 4:05pm PDT Sunday, 19 July 2026 Room 403 B

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Games

Geometry

Hardware

Image Processing

Performance

Pipeline Tools and Work

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionOur system solves difficult VFX matchmoves by fusing LiDAR geometry with Deep Optical Flow. Unlike traditional corner-detection, it leverages dense geometric constraints to handle motion blur and dynamic occlusion. The system features automated actor masking and a novel re-anchoring architecture that eliminates drift, delivering accurate camera solves for production pipelines.

People

Srdjan Milosevic

Progressing Level-of-Detail Animation for Volumetric Elastodynamics

Technical Paper

10:45am - 10:55am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe extend Progressive Dynamics [Zhang et al. 2024, 2025] from cloth and shells to volumetric finite elements, enabling an efficient level-of-detail (LOD) animation-design pipeline with predictive coarse-resolution previews for rapid iteration toward a final high-resolution volumetric elastodynamics animation.

People

Technical Paper

Progressive Photorealistic Simplification

9:20am - 9:30am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a method for simplifying photorealistic scenes by progressively removing elements based on semantic importance. Our framework systematically removes elements in a hierarchical order, using generative inpainting to maintain photorealism throughout the process. This generates plausible photograph sequences, enabling applications like content-aware decluttering, layer decomposition, and interactive editing.

People

Hebrew University of Jerusalem

Real-Time Live!

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionPAIC is a virtual camera that allows any camera feed to be adjusted in real time, using text prompts. No complex software or expensive hardware required. What you want is what you get: the AI adjusts it live - whether it's an avatar, effect or background.

People

Jeroen Cluckers

AP University of Applied Sciences and Arts Antwerp

Joshua Hall

AP University of Applied Sciences and Arts Antwerp

Lowie Spriet

AP University of Applied Sciences and Arts Antwerp

Technical Paper

Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions

11:35am - 11:45am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionProx-E is a training-free framework for fine-grained 3D shape editing that uses a primitive-based geometric proxy to explicitly control structural changes. By editing this proxy with a VLM and guiding a 3D generative model accordingly, it enables localized, identity-preserving edits that outperform prior 2D-driven and training-based 3D editing approaches.

People

Technion - Israel Institute of Technology

Or Litany

Technion - Israel Institute of Technology

Technical Paper

PureSample: Neural Materials Learned by Sampling Microgeometry

11:05am - 11:15am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionPureSample is a neural BRDF representation that learns material appearance directly from forward random walks on microgeometry. It enables efficient BRDF evaluation, importance sampling, and pdf evaluation using a flow-based sampler and a lightweight view-dependent albedo network, supporting complex homogeneous and spatially varying materials.

People

Technical Paper

Quads & Singularities - Interactive Discussion

10:00am - 10:30am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

Technical Paper

Quantifying reality of ultra-realistic 3-D displays - the effect of resolution and contrast

4:35pm - 4:45pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe built an ultrarealistic display system capable of reproducing 3D scenes with such fidelity that they are indistinguishable from their real counterparts. Then, we used the display to measure how reducing resolution and contrast affects perceived realism.

People

Joseph Gerard March

Dounia Hammou

Simon J. Watt

Bangor University

Rafał K. Mantiuk

Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axes

Technical Paper

4:05pm - 4:15pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe introduce an implicit method for medial axis extraction from point clouds and meshes, addressing challenges in noisy or incomplete data. By connecting the signed distance field and the medial field, we reformulate the problem as implicit reconstruction, offering a novel, robust solution for accurate medial axis computation.

People

Jiayi Kong

S-Lab Nanyang Technological University

Chen Zong

S-Lab Nanyang Technological University

School of Mathematics Nanjing University of Aeronautics and Astronautics

Jun Luo

School of Computer Science and Technology Shandong University

Shiqing Xin

Nanyang Technological University (NTU)

Jiayi Kong

Technical Paper

R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

2:00pm - 2:10pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present R-DMesh, a novel feed-forward video-guided mesh animation framework that solves the pose misalignment dilemma between an initial mesh and a condition video through jump offset modeling. It generates high-fidelity, motion aligned 4D animations and enables downstream applications like pose retargeting and holistic 4D generation.

People

Zijie Wu

RaDe-GS: Rasterizing Depth in Gaussian Splatting

Technical Paper

4:25pm - 4:35pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionGaussian Splatting enables high-quality, real-time novel-view synthesis, but extracting detailed 3D geometry remains challenging. We introduce a rasterized approach to render the depth and normal maps for general 3D Gaussian primitives. Our method significantly enhances shape reconstruction accuracy while maintaining the computational efficiency of Gaussian Splatting.

People

Baowen Zhang

Chuan Fang

Rakesh Shrestha

Yixun Liang

xiaoxiao Long

Ping Tan

Baowen Zhang

Radiance Caching for Differentiable Path Tracing

Technical Paper

9:30am - 9:40am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a spatially blended radiance-caching framework for differentiable path tracing that improves speed and robustness in material recovery under unknown lighting.
By jointly optimizing cache, materials, and blending, the method produces physically meaningful materials that generalize to new lighting conditions.

People

Ziyi Zhang

Google

Radiance Fields from Photons

Technical Paper

2:40pm - 2:50pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionNeural radiance fields and Gaussian splats often produce artifacts in low light, high dynamic range, or with rapid motion. Instead, by training at the granularity of individual photons, as enabled by single-photon cameras, we can achieve sharp, reliable reconstructions even in these challenging conditions.

People

Sacha Jungerman

Aryan Garg

Mohit Gupta

Sacha Jungerman

Ragged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings

Technical Paper

2:30pm - 2:40pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionRaNAD is the first spatiotemporal neural denoiser for deep Monte Carlo renderings. It handles semi-structured deep images with variable bin counts per pixel through ragged neighborhood attention, and exploits temporal context across up to seven frames, greatly advancing in both quality and temporal stability for denoising deep images.

People

Xianyao Zhang

Gerhard Röthlin

Tunc Ozan Aydin

Farnood Salehi

Marios Papas

Rao-Blackwellized Markov chain Monte Carlo Light Transport

Technical Paper

2:20pm - 2:30pm PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a novel Rao-Blackwellization technique for variance reduction in Markov chain Monte Carlo light transport. We improve both Metropolis Light Transport and the current state-of-the-art, Jump Restore Light Transport, consistently outperforming traditional variance reduction, accelerating convergence, and establishing a new state-of-the-art in MCMC-based rendering under equal-time and equal-sample evaluations.

People

Sascha Holl

Saarland University

Gurprit Singh

Hans-Peter Seidel

Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction

Technical Paper

9:20am - 9:30am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionRaster2Seq is an anchor-based autoregressive formulation that frames floorplan reconstruction as scalable, sequential polygon prediction, transforming rasterized floorplan images into vectorized format. Through using our proposed labeled polygon sequence representation, the method jointly encodes spatial and semantic attributes, overcoming fixed-query budget limitations while significantly improving robustness as floorplan complexity increases.

People

Industry Session

Ray-Traced Gaussian Splats in Production: The June July Pipeline

10:00am - 10:50am PDT Tuesday, 21 July 2026 Room 511C

Production & Animation

Animation

Pipeline Tools and Work

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionBuilding on the VidViz workflow introduced at SIGGRAPH 2025, this talk documents the next phase of the June July virtual production pipeline. We describe how VidViz planning tools informed the live-action shoot, and how captured location data was transformed into an HDR Gaussian splat using a combination of the XGrids scanner and the Arri Alexa 35. We detail the process of integrating that asset into Chaos Arena and the advantages of working with ray-traced splats in a flexible, real-time stage environment, including lighting evaluation, camera planning, and interactive iteration before a single frame of principal photography is committed.

People

Chris Nichols

Chaos

Technical Paper

RCGP: Resource Contracts for Graphics Programming

9:50am - 10:00am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionRCGP introduces a type system for graphics programming that statically enforces resource contracts, the agreements on type, layout, binding, and synchronization between shaders, pipelines, and host code. Through contracts, modules, combinators, and witnesses, RCGP catches descriptor mismatches, layout drift, and missing barriers at compile time, eliminating common classes of errors.

People

Venkataram Sivaram

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Sai Praveen Bangaru

Ravi Ramamoorthi

Tzu-Mao Li

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Jonathan Ragan-Kelley

Fredo Durand

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Technical Paper

ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting

9:30am - 9:40am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a reinforcement learning-based retargeting method that transfers human motion to diverse morphologies, including humanoids and a quadruped, without artifacts such as foot-sliding, hovering, or self-penetration. A bilevel optimization framework refines upper-loop retargeting parameters defined via sparse semantic correspondences while training the lower-loop RL policy, eliminating manual correspondence tuning.

People

Technical Paper

Real-Time GPU Vector Graphics SDF Generation Based on Quadratic Stroke Rendering

11:15am - 11:25am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a GPU-based algorithm for real-time signed distance field generation from quadratic vector graphics. By treating SDF computation as parallel stroke rendering, the method achieves substantial speed improvements over CPU approaches, enabling dynamic text, interactive user interfaces, and real-time distance-based visual effects.

People

Xuhai Chen

Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University

Guangze Zhang

Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University

Juan Cao

School of Mathematical Sciences, Xiamen University

Zhonggui Chen

Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University

Technical Paper

Real-Time Level-of-Detail rendering with ReSTIR

9:30am - 9:40am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose a method to overcome a limitation in ReSTIR path tracing by introducing a surface point mapping to reuse samples across frames containing meshes with different topologies and enabling real-time LoD rendering with ReSTIR.

People

Yu-Chen Wang

Real-Time Rendering - Interactive Discussion

Technical Paper

4:35pm - 5:05pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Games

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

Birds of a Feather

Real-Time Shading BOF: Building a Community Around Shaders, Shading Languages, and Tech Artist Workflows

1:00pm - 2:30pm PDT Tuesday, 21 July 2026 Room 518

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Augmented Reality

Games

Graphics Systems Architecture

Hardware

Image Processing

Industry Insight

Pipeline Tools and Work

Real-Time

Rendering

Scientific Visualization

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThe Real-Time Shading BOF, with Ken Perlin and Marc Olano, aims to foster a vibrant, cross-disciplinary community of researchers, technical artists, hardware vendors, compiler developers, and practitioners working with shaders and shading languages. Building on the 2026 Shading Languages Symposium, this session will focus on practical pain points faced by technical artists in production environments—such as shader authoring, debugging, portability, performance, and integration with modern real-time pipelines—while welcoming insights from language designers and hardware experts. The BOF will serve as an informal forum for discussion, idea exchange, and networking, acting as a forerunner to the Real-Time Shading Symposium in 2027.

People

University Of Maryland, Baltimore County

Technical Paper

Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures

3:55pm - 4:05pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionThis paper investigates how avatar and face representation influence the perceptual evaluation of synthesized co-speech gestures. Across three controlled experiments, it shows that visual presentation systematically biases judgments of motion quality and provides practical recommendations for fairer, more reliable benchmarking of gesture generation systems.

People

Haoyang Du

Technological University Dublin

Yinghan Xu

Trinity College Dublin

John Dingliana

Trinity College Dublin

Brian Keegan

Technological University Dublin

Rachel McDonnell

Trinity College Dublin

Cathy Ennis

Maynooth University

Technical Paper

Reciprocal Latent Fields for Precomputed Sound Propagation

3:55pm - 4:05pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Games

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWave-coding methods for sound propagation in games are very memory-intensive. We present Reciprocal Latent Fields leveraging Riemannian metric learning to reduce memory usage by orders of magnitude. Our method infers relevant acoustic parameters nearly instantaneously and results in perceptually identical sound quality to the ground truth wave coding.

People

Hugo Seuté

Ubisoft Divertissements Inc.

Technical Paper

Reconstruction & Sampling - Interactive Discussion

11:55am - 12:20pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

Technical Paper

Reconstruction - Interactive Discussion

11:55am - 12:25pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Ref-DGS: Reflective Dual Gaussian Splatting

2:50pm - 3:00pm PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionRef-DGS is a dual Gaussian splatting framework that decouples surface reconstruction and specular reflection, modeling near- and far-field specular reflections without ray tracing, achieving efficient, high-quality surface reconstruction and novel view synthesis.

People

Institute of Automation, Chinese Academy of Sciences

Peter Wonka

King Abdullah University of Science and Technology (KAUST)

Spatial Storytelling

REfact: Growing with Movement – A Hybrid Performance

3:00pm - 3:45pm PDT Wednesday, 22 July 2026 Concourse Hall

New Technologies

Performance

Rendering

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionREfract is a hybrid performance where a dancer and avatars coexist, evolve, and shift agency
through motion capture and live rendering. In a 15-minute performance, set in a minimalist
desert landscape with floating letters, the piece explores transformation, spatial perception, movement-driven storytelling, presence, autonomy, physical-digital interaction.

People

Zelia ZZ Tan

TechDanceLab

Immersive Pavilion

Reframe: Collaborative AI Scene Editing in 360° Multiplayer VR

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionReframe is a multiplayer VR experience where groups collectively edit 360° photographs using generative AI. Participants inhabit panoramic environments then point at areas while speaking about what they want to see. The system transcribes their dialogue into prompts and composites AI-generated imagery into the shared scene to elicit further prompting.

People

Marty Miller

City University of Hong Kong, School of Creative Media

University of Lapland

Tesfa Yohannes

Hong Kong Polytechnic University

Technical Paper

Relit-LiVE: Relight Video by Jointly Learning Environment Video

2:00pm - 2:10pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionRelit-LiVE produces physically consistent and temporally stable relighting results without requiring prior knowledge of the camera pose. It utilizes raw reference images to ensure realistic lighting effects and introduces a joint prediction framework generating relighting videos with frame-level warped environment maps, consistently outperforming state-of-the-art methods across benchmarks.

People

University of Chinese Academy of Sciences China

Tianqi Liu

The Chinese University of Hongkong

Shaocong Xu

BAAI

Chongjie Ye

Course

Remesher: Automate Character Pipelines with ComfyUI's API, Docker, and Agents

2:00pm - 5:15pm PDT Thursday, 23 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionLearn to build automated character generation pipelines using ComfyUI's REST/WebSocket APIs. Deploy state-of-the-art open source image generation and 3d generation models (Qwen, Hunyuan3D) via Docker and cloud GPU providers, then build Typer CLI tools that transform text prompts into rigged 3D characters through programmatic workflow execution: generate→turnaround→mesh→rig.

People

Michael Gold

School of Visual Arts

Depth Map Ventures

Birds of a Feather

Remote Production in 2026: What actually works?

10:00am - 11:00am PDT Thursday, 23 July 2026 Room 513

New Technologies

Production & Animation

Industry Insight

Performance

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionRemote production is no longer experimental. Across animation, VFX and real-time studios, distributed workflows are now central to production operations. Yet key questions remain: which remote and hybrid models are sustainable, and how can studios balance security, infrastructure costs, operational complexity and access to global talent?
This Birds of a Feather session brings together technology leaders from animation studios and the production technology ecosystem to share lessons learned from large-scale deployments. Topics include workstation access, multi-site production, cloud and hybrid infrastructure, pipeline operations, security and evolving remote technologies. Attendees will compare experiences and identify effective industry practices.

People

Jean-Christophe Rodier

Miraculous-TF1 Studio

Birds of a Feather

Renderfarming: This is an annual discussion of VFX & Animation Large-Scale Rendering, On-prem and Hybrid Farm

10:00am - 11:00am PDT Tuesday, 21 July 2026 JW Marriott - Plaza 1

New Technologies

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Hardware

Industry Insight

Full Conference Supporter

Full Conference

Experience

DescriptionThis is an annual discussion of Large-Scale Rendering. With render farm infrastructure, both on-premise and hybrid cloud solutions have software, queue management, reliability, and performance woes. Industry experts and new entrants are all welcomed, for a sharing of knowledge, experience, and best practices. Mail joe@jdamato.com for any questions or comments. This is part of a linked series of Technical Pipeline BoFs, covering the VFX Reference Platform, Renderfarming, Cloud Native, Pipeline, Studio Storage, and Agentic Workflows

People

Joe D'Amato

CDW StudioCloud

A Cup of Joe VFX on YouTube

Jeff Rochlin

Framestore

Technical Paper

ReRoPE: Repurposing RoPE for Relative Camera Control

9:20am - 9:30am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Full Conference Supporter

Full Conference

DescriptionReRoPE is a plug-and-play framework for controllable video generation that achieves precise camera control by injecting relative pose information into the underutilized low-frequency bands of standard Rotary Positional Embeddings (RoPE).

People

Production Session

Research to Reality: Scaling Generative AI for The Wizard of Oz at Sphere

4:15pm - 5:15pm PDT Sunday, 19 July 2026 Petree D

Arts & Design

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Display

Education

Generative AI

Image Processing

Industry Insight

Performance

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionAdapting the 1939 classic The Wizard of Oz for the 16K x 16K immersive canvas of Sphere presented a unique technical paradox: how to translate nearly century-old, 4:3 analog footage into a fully immersive environment. Initiated at a time when viable generative video models did not yet exist, and requiring bespoke solutions beyond the capabilities of emerging commercial tools, this session reveals the collaborative R&D workflow between Sphere Studios, Magnopus, and Google DeepMind.

Panelists will dissect the hybrid production pipeline used to solve the project's most complex challenges: Generative Super Resolution, Character Outpainting, and AI Performance Generation.

First, the panel will address the image fidelity challenge. On Sphere’s media plane, the original film grain appeared as massive visual noise. The team will detail the development of novel upscaling architectures designed to fundamentally modernize the footage. We will demonstrate how these custom models suppressed legacy artifacts and synthesized new high-frequency detail, creating sharpness and texture comparable to modern digital cinema, while maintaining the temporal coherence required for large-format playback.

Second, the session explores the integration of generative elements into a traditional VFX environment. While traditional vendor workflows handled the massive environmental extensions, the team utilized Generative AI to solve the complex character continuity challenges. We will detail the use of Character Outpainting to seamlessly complete characters partially cropped by the original 4:3 frame, alongside the generation of new AI Character Performances for those who walked completely out of view. The team will discuss the strategies used to ensure these generated assets matched the distinct physical language of the original actors.

Finally, the session covers the engineering hurdles of orchestrating this hybrid pipeline. We will examine how the team managed the ingest of disparate high-resolution generative elements to deliver a unified, temporally stable 16K master for the world’s largest high-resolution LED screen.

Since its debut, this pioneering effort has become one of the most commercially successful generative AI deployments in entertainment history, driving record-breaking audiences at Sphere. Validating the success of this hybrid R&D approach, the project earned the prestigious PGA Innovation Award and the VES Award for Outstanding Visual Effects in a Special Venue Project. Attendees will leave with a proven roadmap for navigating the intersection of generative AI research, traditional VFX, and next-generation immersive storytelling.

People

Rudy Grossman

Director of Gen AI

Magnopus

Irfan Essa

Principal Research Scientist

VP of Technology

Senior Staff Research Engineer

CEO

Director of Production Technology Innovation

Sphere Entertainment Co.

Technical Paper

Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids

11:35am - 11:45am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a variance-adaptive voxel grid that adjusts size based on local SDF variance. Using a flat spatial hash table, it achieves constant-time access, memory efficiency, and full GPU parallelism. Additionally, a parallel quad-tree structure supports GPU-accelerated Gaussian Splatting rendering, enabling effective control over splat density.

People

Lorenzo De Rebotti

Emanuele Giacomini

Giorgio Grisetti

Luca Di Giammarino

Sapienza, University of Rome

Lorenzo De Rebotti

Art Paper

Resonance: Meditative Neural Rhythms as Collective Spatial Experience

9:20am - 9:40am PDT Tuesday, 21 July 2026 411 Theatre

Arts & Design

Research & Education

Animation

Art

Audio

Augmented Reality

Capture/Scanning

Dynamics

Hardware

Lighting

Performance

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionResonance transforms a traditionally solitary meditative practice into a shared spatial experience by externalizing a meditator's neural rhythms as architectural-scale light and motion. Rather than treating neurofeedback as private data, the work situates cognition within an immersive environment that can be collectively sensed and inhabited. Bridging contemplative traditions with computational design, it expands bio-responsive systems beyond subjective interaction toward shared, embodied engagement and collective awareness.

People

Ruipeng Wang

Yuxiang Cheng

Zhiyan Xing

Media Lab, Massachusetts Institute of Technology (MIT)

Behnaz Farahi

ReSTIR BDPT: Bidirectional ReSTIR Path Tracing with Caustics

Technical Paper

9:20am - 9:30am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionReSTIR accelerates path tracing by reusing samples between pixels. However, existing methods are limited by the sampling quality of path tracing, making them inefficient for scenes with caustics and hard-to-reach lights. We develop a ReSTIR variant incorporating bidirectional path tracing that significantly improves the sampling quality in these scenes.

People

Trevor Hedstrom

Rethinking the Render-Display Pipeline to Reduce Latency in Interaction

Trevor Hedstrom

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose an integration of render and display that reduces interactive latency far below delays in current systems -- our measurements show click-to-photon latency below 2 ms. We will demonstrate a low-resolution hardware prototype of this integrated pipeline along with a high-resolution interactive simulator of alternative display scans.

People

Evan Jonson

Francis Marion University

Aaron Fulmer

Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing

Technical Paper

4:25pm - 4:35pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Fabrication

Haptics

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present a computational fabrication pipeline for retrofitting 3D objects with real-time multi-touch sensing without modifying their interiors. From a 3D scan, our method routes and optimizes surface-conforming electrode layouts under geometric, fabrication, and hardware constraints. We guide assembly via projection to enable precise spatial input sensing on curved objects.

People

Independent Researcher

Christian Holz

Ringling College of Art and Design

Computer Animation Festival

Right Hand Man

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionNo one likes to be a third wheel on a first date. Right Hand
Man pushes the boundaries of this concept with its two main
characters, Lucas and Cade, twin brothers who are a human
and a hand puppet, respectively. We follow their journey as
Lucas tries to navigate his first date with the lovely Cristine at a
fine dining restaurant, attempting to hide Cade away to
masquerade as an average guy. All Cade wants to do, though,
is get in on the excitement and romance of the experience. Will
Cade make himself known to Cristine? Will Lucas learn that
hiding your true self is the worst foundation for a first date?
Watch and find out!

People

Emma Greenman

Director

Yaumara Carrion

Director

Ringling College of Art and Design

Talks

Rigs2Emotion: Automatic emotion classification from facial rigs

4:05pm - 4:25pm PDT Wednesday, 22 July 2026 Room 515 A

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Audio

Computer Vision

Performance

Full Conference Supporter

Full Conference

DescriptionWe present Rigs2Emotion, a ML tool based on rig controllers values to classify emotions of animations frames accurately. It can be used on any production, is character- and rig-specific and is much more data-efficient than more usual method using audio or image fine-tuned pre-trained models.

People

Stage Session

RigX: Rethinking How Characters Are Rigged

2:00pm - 2:30pm PDT Tuesday, 21 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Animation

Art

Augmented Reality

Capture/Scanning

Digital Twins

Games

Industry Insight

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionMarko Š. presents RigX, a next-generation character rigging and deformation pipeline designed to rethink how digital humans are built for high-end games and cinematic production. Unlike traditional approaches that rely on heavy muscle simulations or complex dependency chains, RigX introduces a lightweight logic-driven deformation system that produces muscle-like behavior with full artistic control and significantly reduced computational overhead.

In this session, attendees will see how RigX enables the creation of both full-body and facial systems with consistent, production-ready performance across a wide range of character styles, from hyper-realistic digital doubles to stylized or cartoony characters. The system is designed for responsiveness, stability, and scalability in real-time pipelines.

The presentation includes a short rendered breakdown followed by a live demonstration of facial animation, body deformation, and rig behavior in real time. Marko will walk through core design principles, integration strategies for advanced production pipelines, and practical considerations for adopting RigX in studio environments.

The session concludes with a focus on production impact, demonstrating how RigX enables significantly faster rigging workflows, simplified setup and iteration, and substantially higher-quality deformation results compared to traditional muscle simulation-based systems.

People

Marko Šašić

RigX Digital Technologies

Miroslav Radmanović

RigX Digital Technologies

Appy Hour

RoboSax Melody Sl0t Machine

5:00pm - 7:00pm PDT Wednesday, 22 July 2026 West Hall A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Games

Generative AI

Geometry

Image Processing

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionMelody Slot Machine has dials with the staves, which can be rotated to change melody variations which are generated by AI-based melody-morphing method. The microcomputer on RoboSax receives MIDI notes from Melody Slot Machine and move servomotors so that the fingering corresponds to the note number.

People

Technical Paper

Robust and Efficient Penetration-Free Elastodynamics without Barriers

9:10am - 9:20am PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Geometry

Hardware

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a barrier-free optimization framework for nonpenetration elastodynamic simulation using a smooth augmented Lagrangian formulation and efficient active-set exploration. Unlike IPC barriers, our method avoids TOI locking, maintains a compact anticipatory constraint set, and delivers faster, robust, visually faithful penetration-free simulation for demanding contact-rich applications.

People

Juntian Zheng

Zhaofeng Luo

Juntian Zheng

Robust Biharmonic Skinning Using Geometric Fields

Technical Paper

4:25pm - 4:35pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionA mesh-free approach for computing bounded biharmonic skinning weights. Our method works well even in presence of severe mesh quality degradation and can incorporate artistic control via weight-painting. It relies on a differentiable field and incorporates boundary handling via hardware accelerated ray-tracing.

People

Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT)

Technical Paper

Robust Computation of Boundary Path Integrals Using Kernel-Density Estimation

9:50am - 10:00am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a simple, robust, and consistent estimator for boundary path integrals in physics-based differentiable rendering. By reformulating boundary integration with kernel-density estimation, our method avoids fragile measure-zero sampling and costly reparameterization. It matches finite-difference derivatives and outperforms state-of-the-art baselines in synthetic inverse-rendering benchmarks with improved efficiency and lower variance.

People

Peiyu Xu

Robust Containment Queries over Collections of Trimmed NURBS Surfaces via Generalized Winding Numbers

Technical Paper

11:05am - 11:15am PDT Monday, 20 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce an accurate and precise generalized winding number method for trimmed NURBS patches based on integrating along boundary curves. For points near a patch, we add a correction term determined via line-surface intersections. The method enables robust inside-outside containment queries that respect curved features in complex CAD models.

People

Jacob Spainhour

Kenneth Weiss

Jacob Spainhour

Robust In-Engine Texture Optimization from Inconsistent Generative Targets

Technical Paper

11:35am - 11:45am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a practical method for optimizing textures directly inside production rendering engines from inconsistent AI-generated images. By handling geometric mismatch and unreliable details, our approach avoids blur and ghosting, enabling robust texture refinement without requiring differentiable rendering or changes to existing pipelines.

People

Taejoon Kim

Electronics and Telecommunications Research Institute (ETRI)

Seung-Uk Yoon

Electronics and Telecommunications Research Institute (ETRI)

Seong-Jae Lim

Electronics and Telecommunications Research Institute (ETRI)

Bon-Woo Hwang

Electronics and Telecommunications Research Institute (ETRI)

Kinam Kim

Electronics and Telecommunications Research Institute (ETRI)

Seung Wook Lee

Electronics and Telecommunications Research Institute (ETRI)

Technical Paper

Robust Planar Maps for 3D Vectorization

10:45am - 10:55am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionVectorizing 3D scenes into 2D vector images requires planar maps to define solid non-overlapping regions. Existing planar map methods are slow and susceptible to numerical instability. We introduce a robust and efficient method for constructing planar maps, using a spatial hierarchy as the fundamental representation of the planar map.

People

Robert Fuchs

Keenan Crane

Roblox

Computer Animation Festival

Games Summit

Rocketship Mai

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionRocketship Mai follows a fearless six-year-old girl who is on a daring mission
to tackle Time (literally) so she can spend more moments with her ailing father.
With her anxious copilot Bunny by her side, Mai speeds through the galaxy to box
clocks, battle oversized foes (like... a million times larger), and take on anything the
cosmos throws in her way.
As the fight escalates, however, Mai discovers that time can’t be stopped — and what
remains is something far more freeing: learning to be fully present with the person she
loves most.

People

Arlyn Nertomb

Producer, Co-Director

Bloomhouse Productions

Nattasha Strestha

Writer, Co-Director

Crystal Woo

Art Director, Co-Director

Airin Budiman

Head of Story, Co-Director

Katie Winchester

Animation Director, Co-Director

Editor, Co-Director

Production Manager, Director

Michelle Lorimer

Composer, Co-Director

Role-Aware Virtual Agents for Navigational Interaction guided by a Multimodal Large Language Model

Technical Paper

3:45pm - 3:55pm PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Fabrication

Haptics

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present a role-aware virtual agent navigation system that generates consistent, role-aligned behaviors. Using multimodal large language models (MLLMs), our approach interprets scene context, user state, and role-context instructions to produce navigation decisions and stylized paths, enabling agents to respond dynamically and behave coherently in immersive environments such as AR.

People

Minyoung Kim

Roll for Reality: Virtual Production Improvised D&D Show

Immersive Pavilion

Spatial Storytelling

3:15pm - 5:00pm PDT Tuesday, 21 July 2026 Concourse Hall

Gaming & Interactive

Games

Performance

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionRoll for Reality is a live, improvised Dungeons & Dragons show integrating tabletop roleplaying, motion capture, AI-assisted narrative tools, and real-time XR visualization. The project explores hybrid XR storytelling frameworks that connect improvisational performance with live virtual production environments.

People

Rene Hernandez-Ayerdis

Educator's Forum

Rolling Through the Pipeline: A Course Model for Virtual Production Education

11:45am - 12:05pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Computer Vision

Digital Twins

Education

Games

Modeling

Pipeline Tools and Work

Rendering

Simulation

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionThis paper presents an introductory virtual production (VP) course built around an LED-wall stage, where students learn VP through embodied, pipeline-centered practice. By integrating cinematography, real-time rendering, tracking, and collaborative workflows, the course develops ecosystem fluency and workflow literacy across film, animation, and game design disciplines.

People

Flip Phillips

David Long

Aidan Montag

Chao Peng

Roto-Lite: Transformer-based Automatic Rotoscoping with Splines

Talks

2:00pm - 2:20pm PDT Sunday, 19 July 2026 Room 403 B

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Education

Games

Generative AI

Image Processing

Simulation

Full Conference Supporter

Full Conference

DescriptionRoto-Lite is a pixels-to-sequence transformer model that parses regions of portrait captures and outputs an efficient set of spline shapes. Our aim is to offer minimal friction between the outputs of our model and its adoption by artists, as compared to more traditional raster-based segmentation models.

People

Sirak Ghebremusse

Otoy, Inc.

Birds of a Feather

Running large-scale, multi-site VFX productions in the real world: what's working & what to fix?

3:00pm - 4:30pm PDT Tuesday, 21 July 2026 Room 513

Arts & Design

New Technologies

Production & Animation

Animation

Industry Insight

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionThis BOF session is a candid conversation about navigating today’s global VFX landscape. We’ll move beyond tax incentive headlines to focus on what truly makes geographically-distributed productions succeed: robust creative pipelines, effective cross-site collaboration, and empowering technology.

We’ll discuss practical realities coordinating work across timezones and cultures, examining how to harness the diverse strengths of global teams to turn geographical distribution into an advantage. We'll address client expectations, how studios balance tax incentive pressures with maintaining creative quality, and how technology helps companies prepare for a future without boundaries.

Together, let’s build the roadmap for our industry’s next chapter.

People

Real-Time Live!

Runway Characters: Real-Time Expressive AI Characters from a Single Image

6:00pm - 7:45pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Computer Vision

Digital Twins

Dynamics

Games

Generative AI

Geometry

Graphics Systems Architecture

Hardware

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

DescriptionRunway Characters is a real-time video agent that generates fully expressive, conversational AI characters from a single image — zero fine-tuning required. Built on GWM-1, Runway's General World Model, it produces lifelike lip-sync, facial expressions, and head motions at 24fps, spanning photorealistic humans to animated mascots.

People

Computer Animation Festival

Saba

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionIn an abstract and symbolic world where gravity is reversed, a unique bond forms between a grandfather and his grandson. As Saba, the grandfather guides the boy through this surreal reality, a violent storm strikes, tearing one of the ropes anchoring their home - and with it, their life together.
After suffering a devastating loss of Saba, the boy embarks on an emotional journey in search of closure. Through a stylized and poetic visual language, the film explores life’s fundamental questions: the paths we take, separation from those we love, and the endless effort to find closure, reconcile loss, and move forward.

People

Liron Topaz

Director

Lirit Rosenzweig Topaz

Computer Animation Festival

Games Summit

Salvation

12:30pm - 1:30pm PDT Sunday, 19 July 2026 411 Theatre

Gaming & Interactive

Games

Full Conference Supporter

Full Conference

Experience

DescriptionSalvation plunges viewers into a world on the brink of chaos, where champions confront both internal and external conflicts that threaten the balance of their realm. The cinematic follows key heroes as they face moral dilemmas, epic battles, and alliances that define the fate of their world. Through cinematic storytelling, dynamic action, and striking visual design, the trailer conveys the tension, stakes, and grandeur of the League of Legends universe.

People

Matt Costa

Director

None

Technical Paper

Sample Matching for Joint Extinction Gradient Estimation in Differentiable Volume Rendering

9:40am - 9:50am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Lighting

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe propose sample matching, a variance reduction principle for differentiable volume rendering. By jointly estimating scattering and transmittance gradient components at shared sample positions, our method reduces gradient variance by up to 80%, significantly improving convergence speed and reconstruction quality in volumetric inverse rendering.

People

Ruihan Yu

Yu-Chen Wang

Jingwang Ling

Feng Xu

SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces

Technical Paper

4:05pm - 4:15pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionSAND is an efficient neural implicit surface representation framework that accelerates sampling by adapting network depth to spatial importance and local geometric complexity. By combining a volumetric depth map with a tailed MLP for adaptive termination, it significantly improves inference-time query efficiency while preserving high-fidelity reconstruction and enabling neural level-of-detail.

People

Chuanxiang Yang

Junhui Hou

Yuan Liu

Siyu Ren

Guangshun Wei

Scalable GPU Construction of 3D Voronoi and Power Diagrams

Technical Paper

2:10pm - 2:20pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a GPU algorithm for constructing large-scale 3D Voronoi and power diagrams. By combining directional geometric culling with hierarchical best-first traversal, our method efficiently handles tens of millions of points across diverse spatial distributions. Applied to mesh-based neural rendering, it removes a key computational bottleneck, enabling higher-fidelity scene reconstructions.

People

Bernardo Taveira

Zenseact

Carl Lindström

Fredrik Kahl

Schrödinger Bridges on Discretized Geometric Domains

Technical Paper

2:20pm - 2:30pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe introduce a spatially discrete formulation of the Schrödinger bridge problem on meshes and grids that enables structure-preserving interpolation between probability distributions. We demonstrate our approach across mesh- and grid-based applications, including displacement interpolation, shape interpolation, and color histogram manipulation, highlighting its ability to achieve geometric fidelity with computational efficiency.

People

Leticia Mattos Da Silva

Mohammad Sina Nabizadeh

Searchable.City: An Open-Vocabulary Semantic Atlas

Emerging Technologies

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionSearchable.City is an open-vocabulary semantic atlas, built by running a vision-language model (VLM) on millions of street-view images to create a searchable visual index of the city. It turns street-level imagery into a map of visual patterns, revealing where architectural styles, infrastructure, culture, and objects concentrate.

People

Sean Hardesty Lewis

Cornell Tech

Talks

Secrets of the Animal Kingdom: Crowds in Disney and Pixar’s Hoppers

2:40pm - 3:00pm PDT Monday, 20 July 2026 Petree D

Production & Animation

Animation

Modeling

Pipeline Tools and Work

Simulation

Full Conference Supporter

Full Conference

DescriptionThis talk presents a hybrid workflow of procedural systems informing physics-driven simulations used to craft the natural crowds in Disney and Pixar’s Hoppers. We will present details of crowds workflows using both SideFx Houdini, and Pixar’s proprietary Presto PCF toolsets to produce hordes of snakes, butterflies, seagulls, and more!

People

Julia Newhide

J.D. Northrup

Jonah Laird

Psy DeLacy

See-through: Single-image Layer Decomposition for Anime Characters

Technical Paper

2:50pm - 3:00pm PDT Monday, 20 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models. Our approach decomposes a single image into fully inpainted, semantically distinct layers with inferred drawing orders — up to 19 layers including hair, face, eyes, clothing, accessories, and more.

People

Jian Lin

Chengze Li

Haoyun Qin

Spellbrush / Shitagaki Lab

Kwun Wang Chan

Yanghua Jin

Spellbrush

Hanyuan Liu

Chun Wang, Stephen Choy

Xueting Liu

SegviGen: Repurposing 3D Generative Model for Part Segmentation

Technical Paper

9:00am - 9:10am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

DescriptionSegviGen is a framework for 3D part segmentation which unifies three settings in one architecture: interactive part segmentation, full segmentation, and 2D segmentation map–guided full segmentation. It improves over sota by 40% on interactive segmentation and by 15% on full segmentation, while using only 0.32% of the training data.

People

Lin Li

Beijing Jiaotong University

Technical Paper

Semantic-Structural Alignment for Generative Pictorial Charts

9:40am - 9:50am PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Generative AI

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionWe introduce a generative framework that transforms traditional statistical graphics into memorable, engaging pictorial charts. It utilizes structural alignment to anchor spatial layouts and semantic alignment to transfer expressive textures. This ensures the resulting visuals are artistically compelling and structurally consistent, advancing data-driven visual storytelling.

People

Immersive Pavilion

SentiSing: An Affect-Driven Immersive Environment for Expressive Vocal Interaction in Virtual Reality

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionSentiSing is an affect-driven VR singing experience where vocal and musical affect jointly control generative visual changes in a forest environment, allowing singers to perceive and explore emotional expression through real-time immersive feedback.

People

Qingzhu Zhang

University of California Berkeley

Educator's Forum

Sew and Code! Understanding How to Construct Bezier Curves

9:40am - 10:00am PDT Tuesday, 21 July 2026 Room 501 ABC

Gaming & Interactive

Research & Education

Education

Games

Image Processing

Modeling

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionThe Sew and Code assignment is designed to fuse programming, math, algorithms, art, and design and provide motivation to Computer Graphics students learning how to construct Bezier curves using the DeCastlejau Algorithm. Students cycle between sewing then programming steps of the algorithm, building up String Art and interactive programs simultaneously.

People

Brittany Morago

University of North Carolina Wilmington

Technical Paper

Shading, Relighting and Volumes - Interactive Discussion

3:00pm - 3:30pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

Emerging Technologies

Shall We Dance? Resonance of Intentions with an Embodied Agent based on the Free Energy Principle

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose an agent grounded in the Free Energy Principle that negotiates intentions through physical interaction. Using a predictive coding-based RNN, the agent dynamically updates internal intentions and time constants to minimize prediction errors, enabling seamless synchronization with human choreography and tempo.

People

Takeru Hashimoto

Sony Computer Science Laboratories, Inc.

Okinawa Institute of Science and Technology Graduate University

Jun Tani

Okinawa Institute of Science and Technology Graduate University

Shunichi Kasahara

Sony Computer Science Laboratories, Inc.

Okinawa Institute of Science and Technology Graduate University

Technical Paper

ShapeUP: Scalable Image-Conditioned 3D Editing

11:45am - 11:55am PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionShapeUp introduces a scalable framework for high-fidelity 3D asset editing. By casting editing as an image-conditioned, latent-to-latent translation, it enables precise local and global transformations while maintaining native 3D consistency. Our approach ensures seamless identity preservation without requiring manual spatial masks.

People

Educator's Day Session

Shaping Future Storytellers: Integrating Advanced 3D, AI and VP Workflows

2:30pm - 3:00pm PDT Monday, 20 July 2026 Room 411

New Technologies

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Education

Generative AI

Pipeline Tools and Work

Full Conference Supporter

Full Conference

Experience

DescriptionTo prepare students for modern workflows, educators must teach the core concepts behind the craft, not just the technical steps to finish a task. Juan Salazar, Foundry’s Creative Director, will review the latest advancements in Nuke’s 3D system, Nuke Stage, and Griptape. Plus, he will discuss how these tools fit into a broader, future-facing vision for AI and virtual production, offering advice on how to train artists who understand how to truly evaluate and direct their tools.

People

Juan Salazar

Foundry

Technical Paper

SHARP-GS: Scalable High-fidelity Accelerated Rendering Pipeline for Ultra-high Resolution 3D Gaussian Splatting

2:30pm - 2:40pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis work introduces a high-performance 3D Gaussian Splatting framework that unlocks real-time 8K rendering for immersive VR. By overcoming architectural bottlenecks, it achieves a massive 2.55× speedup and sustains over 250 FPS, delivering high-fidelity, 120 Hz stereoscopic experiences without compromising visual quality.

People

JunRan Ding

WeiHang Liu

YuKe Li

YiZhou Wang

AnTong Li

QiHan Ding

Xin Lou

JingYi Yu

SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability

Technical Paper

2:10pm - 2:20pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe propose SharpNet, an enhanced MLP architecture that augments the input with a feature function to produce controllable derivative jumps. We show that SharpNet can preserve the sharpness in the intended regions while maintaining smoothness elsewhere, and that it outperforms baseline methods in sharpness-critical tasks such as CAD reconstruction.

People

Hanting Niu

Junkai Deng

Wencheng Wang

Shellular Metamaterial Design via Compact Electric Potential Parametrization

Technical Paper

4:15pm - 4:25pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionThis work introduces a compact, expressive design space for shellular metamaterials, along with a fast GPU-based homogenization pipeline that evaluates elastic properties in near real time. This enables interactive exploration and inverse design, achieving diverse geometries and a broad range of mechanical behavior at low solid volume.

People

Tianyi Huang

Chang Liu

Bohan Wang

SIGGRAPH 2026 Experience Hall Awards

Emerging Technologies

Immersive Pavilion

12:00pm - 12:30pm PDT Thursday, 23 July 2026 Concourse Hall

Full Conference Supporter

Full Conference

Experience

DescriptionJoin us on the Spatial Storytelling stage in congratulating the recipients of the SIGGRAPH 2026 Experience Hall Awards.

Immersive Pavilion
- Best in Show

Emerging Technologies
- Official Selection — Digital Content Association of Japan
- Official Selection — Laval Virtual
- Best in Show
- Audience Choice Award

We celebrate these exceptional achievements and the creators whose work continues to push the boundaries of innovations in graphics, interaction, and immersive experiences.

Keynote Speaker

SIGGRAPH 2026 Opening Session & SIGGRAPH 2026 Keynote: Lanny Smoot, Inventions, Innovations, and Imagination: Lanny Smoot’s Prolific Path

9:00am - 10:30am PDT Monday, 20 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionOne of Disney’s most prolific inventors is taking the SIGGRAPH 2026 stage for an exciting presentation that will have attendees reflecting on the power of research, activating emerging technologies, and the value of cross-industry connections to drive technological advancements in one’s career.

Lanny Smoot will share some of the significant inventions and innovations he’s made during his long career in research and development, starting by working backward through his 27 years at Walt Disney Imagineering R&D and to his earlier 20-year career at the nation’s telecommunications giants: Bell Labs, Bellcore, SAIC, and Telcordia.

Along the way, Lanny will invite us into his lab and will describe the career lessons he’s learned — the importance of both research and new ideas and the necessity for collaboration between people with disparate talents. He will describe how he, and many engineers and scientists, are inspired to come into their fields and how young practitioners can find success.

As a long-time contributor to and friend of SIGGRAPH, Lanny will reflect on some of his professional contributions to the conference, including the Emerging Technologies systems he’s dreamed up: “The Electromagnetic Eye”, “Volumetric Display”, “The Interactive Holographic Zoetrope”, and the “Interactive Ping Pong Ball Zoetrope”.

Come for a story of meaningful advancements that revolutionized entertainment and communication, and be inspired by a unique career path built on imagination and taking technology to the next level.

People

Lanny Smoot

Disney Research

ACM SIGGRAPH 365

Art Gallery

Art Paper

SIGGRAPH Art Party - Joint Event by DAC, Art Paper & Art Gallery

5:30pm - 9:00pm PDT Sunday, 19 July 2026 Hotel Per La, Autograph Collection, 649 S Olive St

Arts & Design

Gaming & Interactive

Research & Education

Art

Education

Full Conference Supporter

Full Conference

Experience

DescriptionHosted by the ACM SIGGRAPH Digital Arts Community, the SIGGRAPH 2026 Art Gallery, and Art Papers, in collaboration with HP, Infinity Festival Hollywood, ASIFA-Hollywood, SONY Pictures Imageworks and ACM SIGGRAPH LA Professional Chapter, this gathering invites you into a warm, vibrant space to meet, share, and connect. Whether you are an artist, designer, researcher, student, or simply curious, come spend an evening with fellow creatives exchanging ideas, stories, and inspiration. Together, we’ll celebrate the diverse art practices that make SIGGRAPH 2026 so dynamic—welcoming new voices, reconnecting with old friends, and enjoying the energy of a shared creative community.

This event now requires an RSVP. Tickets will be issued based on availability. Please register here: https://www.xsovip.com/siggraph.

Event Meeting Location: Hotel Per La Rooftop, Bar Clara, 649 S Olive St

People

SIGGRAPH 2026 Art Paper

ACM SIGGRAPH LA Professional Chapter

Lex Dreitser

LAUNCH SESSION & WHITE LABEL AR, INFINITY FESTIVAL Hollywood

Birds of a Feather

SIGGRAPH Asia 2026

11:00am - 12:00pm PDT Monday, 20 July 2026 Room 510

Research & Education

Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionSIGGRAPH Asia 2026, the 19th ACM SIGGRAPH conference and exhibition on computer graphics and interactive techniques in Asia, will take place from 1 to 4 December 2026 at the Kuala Lumpur Convention Centre KLCC, Malaysia, its first edition in the country. As the sister conference to SIGGRAPH, it travels across Asia, blending innovation with local culture. This session is designed for those new to SIGGRAPH Asia, offering a clear introduction to what the conference is about, how to participate, and what to expect. It also provides an open platform to ask questions, exchange ideas, and connect with the community.

People

ACM SIGGRAPH 365

SIGGRAPH for Beginners - Meet & Greet

4:30pm - 5:00pm PDT Sunday, 19 July 2026 Room 409 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Networking

Full Conference Supporter

Full Conference

Experience

DescriptionThe SIGGRAPH for Beginners - Meet & Greet is a continuation of the session that will help you learn and navigate the conference like a pro.

Featuring delicious snacks, this is the way to kick off the conference in style!

Special thanks to our donors: Das Element (Germany) and Animationsinstitut of Filmakademie Baden-Wuerttemberg (Germany).

People

Technical Directing Senior Lecturer

Technical Directing Senior Lecturer

SIGGRAPH for Beginners - Welcome to the Conference!

ACM SIGGRAPH 365

3:30pm - 4:30pm PDT Sunday, 19 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Education

Games

Hardware

Scientific Visualization

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionNew to SIGGRAPH? Returning after a SIGGRAPH-break? Just curious about what the conference has to offer? If your answer is YES to any of these questions, this session is your friendly introduction to the week ahead.

SIGGRAPH for Beginners will help you make the most of your time at the conference. You'll get practical tips, helpful context, and a chance to ask questions in a relaxed setting.

Topics include:
- How to navigate the conference and its program
- Where to find help and support during the week
- Top Programs you won’t want to miss
- An introduction to ACM SIGGRAPH, the organization behind the event

Bring your questions and curiosity—and stay until the end for our Meet & Greet, featuring drinks and snacks, to kick off the conference in style!

NOTE: The session will take place from 3:30 - 4:30 pm in 404 AB. The Meet & Greet from 4:30 - 5:00 pm in 409 AB.

People

Technical Directing Senior Lecturer

Technical Directing Senior Lecturer

Mikki Rose

Cloth and Hair TD/Hair Groomer

Jim Kilmer

SIGGRAPH Pathfinders Chair

The OPAL Group

Chris Redmann

SIGGRAPH 2026 Conference Chair

Apple

June Kim

ACM SIGGRAPH EC Chair

SIGGRAPH for Health: Convergence of Trends and Techniques

ACM SIGGRAPH 365

1:00pm - 2:00pm PDT Tuesday, 21 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Education

Ethics and Society

Games

Performance

Physical AI

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionSIGGRAPH is the perfect platfom to create impact in a world that increasingly needs care!

This session is the most desired follow-up to the conversations on how the convergence of AI, computer graphics, and immersive media is transforming healthcare. To ensure adoption, these innovations must combine science and human-centered perspectives. Gathering research, technology and culture, SIGGRAPH is a core player in this domain.

This year's SIGGRAPH for Health is part of the ACM SIGGRAPH 365 program. The session is designed as a one-hour event, beginning with a brief introduction to the initiative, followed by a series of lightning talks, and concluding with a panel discussion featuring SIGGRAPH contributors whose work connects computer graphics and health.

People

Technical Directing Senior Lecturer

Nicolas Henchoz

EPFL+ECAL Lab

Technical Directing Senior Lecturer

Davide Corigliano

PhD student at ETH Zurich

Yi-Chin Lee

Graduate in Doctor of Medicie and Computer Science

SIGGRAPH Roundtables: Beyond the Talk

Tim McGraw

Associate Professor

Purdue University

Talks

3:45pm - 5:25pm PDT Monday, 20 July 2026 Room 409 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Lighting

Pipeline Tools and Work

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionEngage. Reflect. Connect.

For its second year, SIGGRAPH 2026 hosts the Roundtables — a series of intimate, speaker-led discussions that carry the conversation beyond the stage. Each 90-minute roundtable seats up to 10 participants in a focused, informal setting. Every table centers on a specific topic drawn from a SIGGRAPH 2026 Talk and is led by the speaker who presented it — a chance to share experiences, ask the questions there's never time for after a Talk, and explore emerging ideas alongside peers and contributors from across disciplines.

Seating is first-come, first-served, so we encourage you to arrive early to join the conversation that resonates most.

Session Format:
Each roundtable follows a simple, engaging structure:
* Opening reflection (3–5 minutes) * Participant introductions (10 minutes) * Group discussion (30 minutes) * Optional table transition (10 minutes) * Stay or explore another topic * Continued discussion (25–30 minutes) * Closing summary (10 minutes)

Roundtable Themes:
Table 1: Engine Room - Real-time VFX & Virtual Production Pipelines, Unreal Engine + OpenUSD with He Sun and Tzung-da Tsai

Table 2: Truth in the Age of AI: Governance, Provenance, and the Future of Evidence with Nira Bozkurt and Charlie Fink

Table 3: From Threads to Theory: Computational Design, Materials, and Quantum Rendering with William Samosir and João Ferreira

Table 4:Spatial Storytelling & Digital Worlds: Gaussian Splatting, Twins, and Immersive Capture with Rory Mitchell, Aj Chavar and Nonny de la Pena

Table 5: Sketch & Synthesize: Artist-Driven AI for Animation, Sound, and Real-Time Performance with Prabal Gupta and Jakob Buhmann

Table 6: Educating the Next Generation: Computer Graphics, AI, Art, and the Future of Animation Learning with Damian Thorn-Hauswirth and Lei Yang

Table 7: Slop or Craft? Human Artistry, Automation, and the Future of Animation Integrity with Lauren Morrison and Christopher Barischoff

Table 8: Look Sharp — Stylized Compositing, Lighting & Lens Craft with Rebecca Lin and Chris Berry

Table 9: Material World — Rendering Realism: Shading, Materials & Light Scattering with Mitch Prater and Artem Kryzhanovskyi

Birds of a Feather

SIGGRAPH Swag Swap and Archive Donation Location

2:00pm - 3:00pm PDT Tuesday, 21 July 2026 Room 512

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Chapters

Computer Vision

Digital Twins

Display

Diversity, Equity and Inclusion

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

History

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Networking

Performance

Physical AI

Pioneers

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionDo you have old SIGGRAPH collectibles or other swag you no longer want? Are you missing that one SIGGRAPH pin and you can’t live without it? Come to the SIGGRAPH Swag Swap and you can trade items with other attendees.

You may also donate unwanted items such as promotional materials, collectibles, publications, and electronic media to the SIGGRAPH History Archive at the Swag Swap. Please check the archive first at https://history.siggraph.org/inventory-view-all/ to see if your item is needed.

People

Lilly Aulls

Niall Williams

Barnard University

ACM SIGGRAPH History Committee

Chair

Matt Adcock

Data61

ACM SIGGRAPH 365

SIGGRAPH Thesis Fast Forward

10:30am - 11:30am PDT Monday, 20 July 2026 Room 404 AB

Research & Education

Education

Full Conference Supporter

Full Conference

Experience

DescriptionThe SIGGRAPH Thesis Fast Forward is a forum for Ph.D. students in computer graphics to present and broadcast their research in 3 minutes or less. Students from around the world introduce us to a wide variety of topics spanning research over the last five years.

People

Siqi Wang

ByteDance Inc.

Shivangi Aneja

Nicole Feng

Tahmeena Javaid Adeel

Bournemouth University

Uday Kusupati

Technische Universität Wien (TU Wien)

Diana Marin

Computer Animation Festival

Silent Night

12:30pm - 1:30pm PDT Thursday, 23 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionA lonely woman living in the forest becomes attached to a wolf and her pup. One night, she wakes up to the sound of a shotgun. Despite the fear, she rushes into the forest, determined to protect them from the menace.

People

Director

Director

Director

Director

Director

Director

Director

Director

Technical Paper

SimArt: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM

9:10am - 9:20am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Robotics

Full Conference Supporter

Full Conference

DescriptionSIMART is a unified multimodal large language model framework that converts static 3D meshes into simulation-ready articulated assets. By jointly modeling part decomposition and kinematics with a sparse 3D VQ-VAE, it reduces token complexity and enables scalable, high-fidelity object generation for robotics and physics-based simulation.

People

Chuanrui Zhang

Nanyang Technological University, Singapore

Nanyang Technological University, Singapore

Art Gallery

Simulacra Naturae - Entangled Biomes: Generative Ecosystems driven by Brain Organoid Intelligence

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionSimulacra Naturae - Entangled Biomes operates as a multisensory infrastructure investigating how aesthetic experience emerges when biological activity, generative algorithms, and embodied agents interact. We position organoid electrophysiology as a coordinating force that mediates relationships across heterogeneous subsystems, spanning visual, sonic, material, and haptic domains. By integrating agent-based simulations with haptic feedback and computational fabrication, the work positions data as a catalyst for emergence. The result is a cyberphysical ecology where distributed neural dynamics and human interaction co-evolve across varying temporal and material scales.

People

Nefeli Manoudaki

Metaesthetica

Iason Paterakis

California State University, Fullerton

Metaesthetica

Stejara Dinulescu

Simulating Memory: Teaching Gullah-Geechee Heritage through Virtual Performances by Community Leaders at a Reconstruction-Era Historical Site

Metaesthetica

Educator's Forum

3:45pm - 4:05pm PDT Wednesday, 22 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Digital Twins

Education

Games

Generative AI

Real-Time

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionNCSU MADTech faculty collaborated with Historic Mitchelville Freedom Park on a sponsored studio course that taught students Gullah-Geechee heritage through the development of virtual scenes that featured digital doubles of community leaders in simulations of park landmarks. Students gained valuable design skills in applying these emerging technologies to a real-world digital heritage research project and earned College global experience credits by learning about the Gullah-Geechee roots of American Black culture from the descendants of the Mitchelville community.

People

Christopher Maraffi

Iyare Oronsaye

Ryan Khan

Simulating Superpowers: From Flailing to Flying in a Controller-Free CAVE

Talks

2:20pm - 2:40pm PDT Sunday, 19 July 2026 Room 408 A

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Capture/Scanning

Computer Vision

Games

Generative AI

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionHow do you make someone truly feel like Superman? Discover how we blended markerless motion capture, 4D effects, cooperative game mechanics, and interactive storytelling in a 3D CAVE to transform physical movements into simulated superpowers for 'Superman Experience: Defenders Unite'.

People

Joey Ziolkowski

Schell Games

Technical Paper

Simulation - Interactive Discussion

11:55am - 12:25pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Animation

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

Technical Paper

Single-shot HDR using conventional image sensor shutter functions and optical randomization

2:40pm - 2:50pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

DescriptionWe present a single-shot HDR imaging method using a global reset release (GRR) sensor and optical shuffling via a random fiber bundle. Our prototype enables HDR recovery with a simple prior and flexible exposure control, demonstrating a dynamic range increase from 48 dB to 73 dB in validation.

People

Single-View Holographic Volumetric 3D Printing with Coupled Differentiable Wave-Optical and Photochemical Optimization

Technical Paper

11:05am - 11:15am PDT Monday, 20 July 2026 Room 408 A

Research & Education

Augmented Reality

Display

Fabrication

Hardware

Real-Time

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe introduce Single-View Holographic Volumetric Additive Manufacturing (SHVAM), a layer-free 3D printing technique that creates microscale structures in seconds using holographic light patterns. Our coupled optical-chemical optimization framework enables ~10 μm lateral features from a mechanically simple, single-view system with broad manufacturing applications.

People

Felix Wechsler

Riccardo Rizzo

Christophe Moser

Sketch2Arti: Sketch-based Articulation Modeling of CAD Objects

Technical Paper

11:45am - 11:55am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionSketch2Arti is the first sketch-based articulation modeling system for CAD objects. Given a CAD model and simple 2D sketches, it identifies movable parts and predicts motion parameters. It can also complete missing internal structures revealed by motion, enabling controllable, iterative, and generalizable articulation modeling for diverse objects.

People

Yi Yang

Changjian Li

Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance

Technical Paper

9:20am - 9:30am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a geometry-aware motion retargeting framework that preserves interaction semantics by performing proximity matching over spatially adaptive anchors. Unlike prior methods with static anchor definitions, our method dynamically repositions anchors to reachable regions on the target character, enabling better preservation of self-contact and near-body proximity under large body-shape differences.

People

Soojin Choi

Korea Advanced Institute of Science and Technology (KAIST)

Seokhyeon Hong

Korea Advanced Institute of Science and Technology (KAIST)

Chaelin Kim

Korea Advanced Institute of Science and Technology (KAIST)

Junghyun Nam

Korea Advanced Institute of Science and Technology (KAIST)

Junhyuk Jeon

Korea Advanced Institute of Science and Technology (KAIST)

Korea Advanced Institute of Science and Technology (KAIST)

Birds of a Feather

Slang in Action: Modern Shading for Graphics, Compute, and AI

1:30pm - 2:00pm PDT Wednesday, 22 July 2026 JW Marriott Diamond Ballroom 1-2

New Technologies

Research & Education

Artificial Intelligence/Machine Learning

Graphics Systems Architecture

Hardware

Performance

Real-Time

Rendering

Full Conference Supporter

Full Conference

Experience

DescriptionJoin the Khronos Group, the Slang project team, and the developer community for an interactive look at the latest advances shaping Slang and modern programmable graphics pipelines. Explore recent project updates, emerging capabilities, real world workflows, and opportunities spanning graphics, compute, AI, and next generation rendering. Bring your questions, share your experiences, and engage directly with the developers and community helping shape what comes next for Slang.

People

Shannon Woods

Smells Like Memory: Reconstructing Virtual Autobiographical Spaces Through Scent in VR

Spatial Storytelling

1:00pm - 1:35pm PDT Thursday, 23 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

Games

Haptics

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionAn immersive VR experience investigates spatial storytelling through the integration of olfactory memory and photographic interaction. By framing photography as a tangible interface for memory recall, the work examines how scent-driven, embodied interaction enables non-linear autobiographical reconstruction and contributes to research on multi-sensory narrative design in virtual environments.

People

Jiaxuan Yin

Smileoyed: Embodied Virtual Pet for Behavioral Affective Synchrony with Multisensory and Biofeedback

Immersive Pavilion

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Computer Vision

Digital Twins

Education

Ethics and Society

Fabrication

Games

Generative AI

Haptics

Hardware

Image Processing

Performance

Pipeline Tools and Work

Real-Time

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionSmileoyed is an embodied virtual pet experienced in mixed reality through a cushion-like device. It uses multisensory outputs driven by users’ respiration and facial-expression biofeedback to evoke affective synchrony. Users gradually perceive a co-present companion that senses and shares their bodily rhythms.

People

Jih-Hsuan Peng

Jung Shen

Yun-Ru Hsu

Zhi Lynn Lay

Kai Hung Wang

Wei-Zhe Zhuang

Ping-Hsuan Han

Yi-Ping Hung

SmoothMotionVectors: Optimizing Your Content for Video Codecs in Free View Video Compression

Technical Paper

10:55am - 11:05am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionConventional video codecs exploit spatial and temporal self-similarity to compress structured signals. We bring this principle to dynamic scene reconstruction with 3D Gaussian Splatting by organizing deformation outputs through a tailored pipeline. The resulting motion vectors are smoother across space and time, allowing greater storage reduction without sacrificing visual quality.

People

Mingyang Song

Yang Zhang

Siyu Tang

Tunc Ozan Aydin

SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control

Technical Paper

2:10pm - 2:20pm PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionSMP builds reusable and modular reward models for training motor controllers. Once constructed from a motion dataset, the priors can be reused across diverse tasks while preserving the behaviors in the data, without requiring access to the original dataset or retraining.

People

Yuxuan Mu

Ziyu Zhang

Yi Shi

Dun Yang

Minami Matsumoto

Kotaro Imamura

National Research Council Canada

Chang Shu

Pengcheng Xi

National Research Council Canada

Xue Bin Peng

Soft Anisotropic Diagrams for Differentiable Image Representation

Technical Paper

2:30pm - 2:40pm PDT Thursday, 23 July 2026 Room 408 B

Research & Education

Display

Generative AI

Hardware

Image Processing

Full Conference Supporter

Full Conference

DescriptionSoft Anisotropic Diagrams (SAD) is a fast, differentiable image representation based on a soft anisotropic additively weighted Voronoi partition (i.e., an Apollonius diagram) with learnable per-site temperatures. It reconstructs images with sharp, content-aligned boundaries, compact storage, fast random access, and substantially faster encoding and higher quality than prior methods.

People

Art Gallery

SOMA: In Search of Somatic Intelligence

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionSOMA is a multisensory robotic sculpture that engages bodily memory as a mode of human–AI communication. Visitors re-enact a remembered movement through a wearable sensing device, while the machine listens, interprets, and responds through its own mechanical choreography, forming an intimate, non-verbal dialogue between human and robotic body. At a time when human–AI interaction is dominated by text-based conversational agents, the work reclaims the body as a site of communication with artificial being, positioning somatic memory as both metaphor and method.

People

Pinyao Liu

Independent Artist

Technical Paper

Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes

11:25am - 11:35am PDT Tuesday, 21 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe introduce S2C-3D, a novel sparse-view 3D reconstruction framework for high-fidelity, complete scene reconstruction. It features three components: a specialized diffusion model for scene-specific image restoration, a training-free view-consistency conditioned sampling process in the diffusion model for refined Gaussian optimization, and a camera trajectory planning scheme for comprehensive scene coverage.

People

Yiyang Shen

The University of Utah

Kun Zhou

Tianjia Shao

Spatially Accelerated Winding Numbers for Curved Geometry

Technical Paper

10:55am - 11:05am PDT Monday, 20 July 2026 Room 403 A

Research & Education

Fabrication

Geometry

Modeling

Rendering

Full Conference Supporter

Full Conference

DescriptionExisting winding number methods for curved geometry, such as SVG and CAD datasets, scale linearly with the number of NURBS primitives. We propose a sublinear approach that leverages a BVH to agglomerate winding number contributions from distant boundary components while maintaining accurate point containment decisions on in-the-wild datasets.

People

Jacob Spainhour

Brad Whitlock

Kenneth Weiss

Spatio-Temporal Control Variates with ReSTIR for Real-Time Rendering

Technical Paper

9:00am - 9:10am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present ReSTCV, a real-time path tracing method that integrates spatio-temporal control variates into ReSTIR. By improving sample reuse beyond single-sample estimation, our approach significantly reduces noise, especially chromatic noise under complex lighting, while maintaining efficiency and requiring only minimal changes to existing ReSTIR pipelines.

People

Zhong Shi

Cunhao Wu

Lifan Wu

Kun Xu

Spatiotemporal FLIP for Fast Free-Surface and Two-Phase Simulation With Very Large Time Steps

Technical Paper

10:45am - 10:55am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present ST-FLIP, a spatiotemporal extension of the Fluid-Implicit Particle (FLIP) method for free-surface and two-phase simulation. ST-FLIP augments particles with 4D spatiotemporal coordinates and supports time steps up to an order of magnitude larger than in existing solvers, delivering several-fold speedups for multi-billion-particle simulations at very high grid resolutions.

People

Bernhard Braun

Rene Winchenbach

Jan Bender

Nils Thuerey

Speedy 3D - Interactive Discussion

Technical Paper

3:00pm - 3:30pm PDT Monday, 20 July 2026 Room 403 B

Research & Education

Geometry

Hardware

Modeling

Rendering

Full Conference Supporter

Full Conference

Keynote Speaker

Sponsored Keynote by Bolt Graphics: Darwesh Singh, Founder, CEO/CTO, Building a GPU for the Future of Computer Graphics

2:30pm - 3:30pm PDT Tuesday, 21 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionWhat happens when you design a GPU to be very efficient at path tracing and physics simulations? It ends up looking different from any other GPU. GPUs were originally designed to be proficient at rasterization. However, the holy grail of computer graphics is real-time path tracing and simulations, which so far has been difficult to achieve with GPUs built around rasterization. Learn how Bolt Graphics is building its very own GPU, Zeus, to achieve real-time path tracing and simulations for creators and researchers around the world.

People

Darwesh Singh

Bolt Graphics

Keynote Speaker

Sponsored Keynote by NVIDIA: Neil Ashton, Ming-Yu Liu, and Edward Liu; Next Era of Graphics — Neural Rendering, World Models, and Simulation

3:45pm - 4:45pm PDT Monday, 20 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionJoin NVIDIA Research and Engineering leaders to experience the latest advances shaping computer graphics and simulation. We will explore breakthrough neural rendering techniques, progress in developing world models, and simulation methods for AI, built by AI.

Through recent research examples and demos, we’ll look at how these technologies are changing the way digital worlds are built, rendered, and used across every domain — creative tools, industrial design, robotics, and autonomous systems.

People

Keynote Speaker

Sponsored Keynote by Tripo AI: Dr. Yanpei Cao, Chief Scientist, The Teapot Test: First It Tested Showing. Now It Tests Making.

2:30pm - 3:30pm PDT Wednesday, 22 July 2026 Hall K

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Discover

DescriptionThe future of interactive media requires a fundamental shift: Moving from manually crafted environments to worlds generated on the fly by the imaginations of millions. Tripo’s core mission is to make this massive-scale, user-generated creation a reality. But to unlock this, we must rethink the entire generative pipeline, spanning from robust individual asset generation to the simulation of completely dynamic environments.

In this deep-dive keynote, Tripo’s chief scientist and research scientists will share the unvarnished journey of building a generative ecosystem from the ground up. We will explore how Tripo scaled from preliminary fundamental research to a robust infrastructure currently serving millions of creators.

The panel will first trace the rapid evolution of the generative landscape by dissecting Tripo’s full-stack approach to 3D generation. Through live demonstrations, the team will highlight key breakthroughs in geometry, topology, texturing, and rigging. These showcases will detail how we are bridging the gap between fundamental AI and graphics research and production-ready pipelines.

However, generating individual assets is only half the equation. To unlock truly interactive user-generated content, the field is rapidly expanding into Generative World Models. The team will share our latest research in this space and explain why we believe World Models will serve as the core engine for next-generation content. Because they simulate physics, dynamics, and continuous interaction without being strictly bound by traditional spatial constraints, these models offer a fundamentally new way to create. Through our latest demos, we will showcase what happens when AI steps beyond creating isolated objects and begins simulating living realities.

Speakers:
Dr. Yanpei Cao, Chief Scientist, Tripo AI

Dr. Yuanchen Guo, Research Scientist, Tripo AI; Dr. Zixin Zou, Research Scientist, Tripo AI; Dr. Yingtian Liu, Research Scientist, Tripo AI; Dr. Biao Zhang, Research Scientist, Tripo AI are lead research scientists at Tripo, with Dr. Zhang also serving as a professor at Xi’an Jiaotong University. Together, they architect the fundamental science and production infrastructure behind Tripo’s full-stack Generative AI platform. Their collective research focuses on overcoming the industry’s hardest generative bottlenecks, directly translating foundational AI breakthroughs into robust, production-ready creator tools. As active open-source contributors and frequent authors in top-tier venues like SIGGRAPH, their work drives the core models that serve millions of creators globally.

People

Yanpei Cao

Tripo AI

Technical Paper

SQuadGen: Generating Simple Quad Layouts via Chart Distance Fields

9:30am - 9:40am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionSQuadGen introduces a diffusion-based approach to simple quad layout generation based on Chart Distance Fields, a continuous representation that encodes discrete quad structures on surfaces. This formulation avoids direct mesh connectivity prediction and enables the synthesis of simple, artist-friendly quad layouts that consistently outperform existing automatic retopology methods.

People

You-Kang Kong

Microsoft

Yue Dong

International Digital Economy Academy

Xin Tong

Anuttacon

Heung-Yeung Shum

Stage Presence: Design and Testing of a Virtual Rehearsal Room Toolset

Talks

4:25pm - 4:45pm PDT Sunday, 19 July 2026 Room 403 B

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Games

Geometry

Hardware

Image Processing

Performance

Pipeline Tools and Work

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionWe present Stage Presence, a multi-user XR rehearsal platform that treats theatrical rehearsal as an embodied spatial storytelling practice. Through practice-based evaluation with professional theatre makers, we show how immersive, role-aware tools can support distributed rehearsal, creative iteration, and spatial memory while surfacing new design tensions around agency and learning.

People

Kevin Laibson

David Gochfeld

Alex Coulombe

Start, Join, Connect: All About ACM SIGGRAPH Chapters

ACM SIGGRAPH 365

3:30pm - 4:30pm PDT Tuesday, 21 July 2026 Room 404 AB

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionThis casual information session will highlight the impact of ACM SIGGRAPH Chapters around the world, provide guidance on how to start or join a professional or student chapter, and offer opportunities to connect and engage with chapter leaders and members of the Professional & Student Chapters Committee (PSCC).

More information about the PSCC, chapters near you and how to get involved can be found at https://siggraph.org/chapters.

People

State of Animation Tools in the industry

ACM SIGGRAPH PSCC

Birds of a Feather

9:00am - 11:00am PDT Tuesday, 21 July 2026 JW Marriott - Plaza 2-3

Production & Animation

Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionWe invite animators, riggers, and engineers to discuss animation tools (third party and
proprietary), workflows and technology trends in the industry.

People

Birds of a Feather

State of Hair in the Industry

9:00am - 11:00am PDT Wednesday, 22 July 2026 Room 518

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Art

Artificial Intelligence/Machine Learning

Education

Games

Industry Insight

Performance

Pipeline Tools and Work

Scientific Visualization

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionA discussion about the current technology and workflow state of hair in the Visual Effects, Animation, Video Games and VR/AR industries. Covering topics that span the entire pipeline of bringing hair to life.

People

Cloth and Hair TD/Hair Groomer

Conference Advisory Group, SIGGRAPH

Skydance Animation

Curtis Andrus

Netflix Animation

Birds of a Feather

State of Rigging Tools in the industry

9:00am - 10:30am PDT Monday, 20 July 2026 JW Marriott - Plaza 2-3

Production & Animation

Animation

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionWe invite animators, riggers, and engineers to discuss rigging tools (third party and
proprietary), workflows and technology trends in the industry.

People

Technical Paper

Statistical Gradient Filtering for Geometry Optimization Under Limited Observations

4:05pm - 4:15pm PDT Wednesday, 22 July 2026 Room 403 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a novel technique that leverages statistical shape space for accurate and robust 3D geometry optimization under limited observations, such as non-rigid registration on partial scans and single-view inverse rendering.

People

Art Gallery

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

DescriptionSternwerk is an interactive installation creating meaning through the constellation of a meteorite (deep time), a simulation (Conway's Game of Life), and human presence. The meteorit, acting as a heat sink for the computation, becomes a condenser for human breath. As each drop falls, amplified by sound, it resets the cellular automata simulation, perpetually restarting a fragile universe. This cyclical process transforms our ephemeral breath into a microcosmic echo of vast temporal scales. The residue carried by each drop becomes a material archive, a humble counter-monument to deep time and human encounters with the cosmic.

People

Alvaro Cassinelli

City University of Hong Kong, School of Creative Media

Tobias Klein

Stochastic geomorphological transport for terrain erosion simulation

School of Creative Media

Technical Paper

11:25am - 11:35am PDT Tuesday, 21 July 2026 Room 403 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionGeomorphological transport is the long-distance transport of quantities which are key elements of terrain erosion. We propose a new stochastic algorithm for the efficient simulation of geomorphological transport with momentum conservation, which enables us, for the first time, to model dynamic emergent deltas, meanders and debris fans in eroded terrains.

People

Nicholas McDonald

erosiv Studio GmbH

Guillaume Cordonnier

Inria, Université Côte d'Azur

Educator's Forum

Stranger Forces: Enhancing Virtual Production with Gen-AI in Real-World College Sponsored Studio Collaborations

2:40pm - 3:00pm PDT Tuesday, 21 July 2026 Room 501 ABC

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Augmented Reality

Capture/Scanning

Education

Ethics and Society

Generative AI

Math Foundations and Theory

Modeling

Performance

Pipeline Tools and Work

Real-Time

Rendering

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionIn spring 2025, NCSU MADTech faculty began teaching our students the targeted use of generative AI tools to solve real-world design problems in sponsored studio projects within our College of Design Virtual Production Lab. This presentation will show how we are teaching MADTech students the ethical integration of these gen-AI tools throughout our virtual production pipeline to better support human artists in achieving their creative visions and prepare students for a changing industry where such technologies are quickly becoming embedded.

People

Christopher Maraffi

Jedidiah Gant

Ryan Khan

Stranger Things: Season 5 - Optimising Workflows Through Advanced Optical Flow And Automated Lighting

Talks

4:05pm - 4:25pm PDT Thursday, 23 July 2026 Room 408 A

Production & Animation

Animation

Artificial Intelligence/Machine Learning

Computer Vision

Graphics Systems Architecture

Image Processing

Lighting

Performance

Pipeline Tools and Work

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present Thistle (an optical flow pipeline) and Marama (an AI-driven automated lighting optimization framework)—two tools enabling scalable, consistent, and high-quality integration of CG characters into live-action plates under demanding production conditions. This presentation details their technical design, pipeline integration, and measured impact in large-scale VFX production.

People

Technical Paper

Streaming of rendered content with adaptive frame rate and resolution

3:45pm - 3:55pm PDT Monday, 20 July 2026 Room 408 A

Research & Education

Games

Real-Time

Rendering

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionTo improve the perceived quality of streamed content while reducing rendering costs, we exploit the spatiotemporal limits of the human visual system and adaptively adjust both frame rate and resolution based on scene content and motion. Those are controlled with a neural network, trained on a dataset of game content.

People

Yaru Liu

Joseph March

Rafał K. Mantiuk

Stress-Aware Panelization of Freeform Surfaces

Meta

Technical Paper

2:10pm - 2:20pm PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Fabrication

Geometry

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present a variational surface rationalization algorithm for creating structurally robust polyhedral approximations of freeform surfaces. Coupling a continuous panelization flow with differentiable shell stress analysis, our method lets structural performance guide the panel decomposition, achieving substantial stress reductions and producing more robust designs than minimizing stress under predetermined decompositions.

People

Xinzhuo Hu

Roi Poranne

University of Haifa

Julian Panetta

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

Technical Paper

11:45am - 11:55am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe propose Strips as Tokens (SATO), a novel framework with a token ordering strategy inspired by triangle strips. By constructing the sequence as a connected chain of faces that explicitly encodes UV boundaries, our method naturally preserves the organized edge flow and semantic layout characteristic of artist-created meshes.

People

Rui Xu

Dafei Qin

Kaichun Qiao

Qiujie Dong

Huaijin Pi

Qixuan Zhang

Longwen Zhang

Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Technical Paper

11:25am - 11:35am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Geometry

Hardware

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionThis work introduces Progressive Semantic Illusions, a novel vector sketching task where a single sketch undergoes a dramatic semantic transformation through the sequential addition of strokes, and presents Stroke of Surprise, a generative framework that optimizes vector strokes to satisfy distinct semantic interpretations at different drawing stages.

People

Huai-Hsun Cheng

Siang-Ling Zhang

Yu-Lun Liu

Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence

Technical Paper

4:15pm - 4:25pm PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe present Structural MAT, a fast and scalable medial axis simplification framework that explicitly tracks the correspondence between medial vertices and surface regions throughout simplification. The method produces clean, structure-aware medial axes with accurate feature alignment and high mesh quality for both organic shapes and CAD models.

People

Pengfei Wang

Qingdao University of Science and Technology

Shuangmin Chen

Dongming Yan

Institute of Automation, Chinese Academy of Sciences

Nanyang Technological University, Singapore

Art Gallery

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Foyer

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Full Conference Supporter

Full Conference

Experience

Description“Stuck in the Middle” is a participatory performance-installation where participants literally wear a conflict between two clashing AI voices. Five pairs of shoulder-mounted wearables embody familiar cultural binaries: good/evil, happy/sad, male/female, rich/poor, fast/slow. With a press of a button, each device captures an image of the participant’s surroundings and sends it to GPT in real-time. The two opposing voices start arguying on what the wearer should or shouldn't do. The work asks what it feels like to be continuously nudged by AI advice, how might LLMs amplify cultural binaries, and whether agency can emerge in the uneasy space in-between.

People

Avital Meshi

UC Davis

Birds of a Feather

Studio Storage: This is an annual discussion of VFX & Animation studios' Large-Scale Storage experiences

2:00pm - 3:00pm PDT Tuesday, 21 July 2026 JW Marriott - Plaza 1

New Technologies

Production & Animation

Artificial Intelligence/Machine Learning

Generative AI

Rendering

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionStudio Storage: Storage for VFX & Animation has extreme requirements and only a limited number of proven solutions are available or you can build your own. Industry experts and new entrants are all welcomed, for a sharing of knowledge, experience, and best practices. Mail joe@jdamato.com for any questions or comments. This is part of a linked series of Technical Pipeline BoFs, covering the VFX Reference Platform, Renderfarming, Cloud Native, Pipeline, Studio Storage, and Agentic Workflows.

People

Joe D'Amato

CDW StudioCloud

A Cup of Joe VFX on YouTube

Amandeep Singh

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

Michele Sciolette

Cinesite Group

Technical Paper

4:25pm - 4:35pm PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Animation

Artificial Intelligence/Machine Learning

Augmented Reality

Rendering

Simulation

Virtual Reality

Full Conference Supporter

Full Conference

DescriptionStyleID is a perception-aware dataset and evaluation framework for measuring facial identity consistency under artistic stylization. By aligning identity similarity with human judgments across styles and strengths, it improves robustness beyond natural-photo face encoders and better supports stylized portrait generation and evaluation.

People

Kwan Yun

Changmin Lee

AYeong Jeong

Youngseo Kim

Seungmi Lee

Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation

Technical Paper

2:20pm - 2:30pm PDT Thursday, 23 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionWe propose a hypernetwork-driven LoRA framework for stylized text-to-motion generation that dynamically modulates a pretrained diffusion model using style embeddings extracted from reference motions. By structuring the style latent space with supervised contrastive learning and incorporating style-guided sampling, the method improves stylization quality, efficiency, and generalization to unseen motion styles.

People

Junhyuk Jeon

Korea Advanced Institute of Science and Technology (KAIST)

Seokhyeon Hong

Korea Advanced Institute of Science and Technology (KAIST)

Korea Advanced Institute of Science and Technology (KAIST)

Technical Paper

STyMo: Fast and Controllable Few-Shot Motion Style Transfer

9:10am - 9:20am PDT Wednesday, 22 July 2026 Room 403 A

Research & Education

Animation

Artificial Intelligence/Machine Learning

Robotics

Simulation

Full Conference Supporter

Full Conference

DescriptionSTyMo is a few-shot approach that learns motion style from only seconds of paired data and trains in one to two minutes. Our key insight is to decompose style into two components: a static component capturing time-invariant posture, and a temporal component capturing frame-wise dynamics.

People

Jose Luis Ponton

Reality Labs, Meta

Universitat Politècnica de Catalunya (UPC)

Talks

Subframe-Aware Transfer of Chain Simulations to Non-Uniform Scaled Rig Controls

11:25am - 11:45am PDT Monday, 20 July 2026 Room 515 A

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Dynamics

Games

Generative AI

Geometry

Modeling

Performance

Pipeline Tools and Work

Real-Time

Simulation

Full Conference Supporter

Full Conference

DescriptionWe present solutions to two challenges in transferring simulated motion to rig controls for real-time game engines: computing local Euler rotations under non-uniform scaling, and eliminating artificial subframe swinging caused by Euler interpolation. Our methods are fast, direct, robust, and support hierarchical joint chains.

People

FunShing Sin

Blizzard Entertainment

Vinod Melapudi

Blizzard Entertainment

Parag Havaldar

Blizzard Entertainment

Technical Paper

Subgrid Marching Tetrahedra

4:45pm - 4:55pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionSubgrid Marching Tetrahedra is an iso-surfacing method that reconstructs high quality surfaces while capturing fine topological features below grid resolution. Using grid edge intersections locations with the implicit function, it produces manifold meshes with the usual benefits from classical marching methods such as easy parallelism and intersection-free property.

People

Hossein Baktash

Successive Height Preintegration for a Height-Interdependent Path Formulation of Multiple Bounces in Smith Microfacet BRDFs

Roblox

Technical Paper

11:25am - 11:35am PDT Tuesday, 21 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionClassic microfacet models for rendering account only for single-bounce light, leading to energy loss. We present a novel multiple-bounce Smith microfacet BRDF with a height-interdependent formulation, successive height preintegration, and an improved BRDF evaluation method. Our model can conserve energy well and achieves low variance with negligible bias.

People

Nara Institute of Science and Technology

Yasuhiro Mukaigawa

Nara Institute of Science and Technology

Hiroyuki Kubo

Chiba University

Technical Paper

SuperSDF:Sparse SDF Super-Resolution for Surface Extraction

3:55pm - 4:05pm PDT Monday, 20 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionSuperSDF is a learning-based method for signed distance field super-resolution that reconstructs high-fidelity meshes from coarse inputs, without mesh supervision or auxiliary surface representations. Using a sparse voxel network near the surface, our approach learns how to directly refine the input SDF, outperforming prior methods in quality, efficiency, and scalability.

People

Technical Paper

Surface chamfering for robust tetrahedral meshing

10:55am - 11:05am PDT Thursday, 23 July 2026 Room 408 A

Research & Education

Geometry

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe describe a new algorithm for conforming high quality tetrahedral meshing with 100% success rate. A novel input "chamfering" that eliminates all acute angles guarantees formal convergence of the underlying Delaunay refinement, while novel implicit Steiner points coupled with indirect geometric predicates ensure numerical robustness along the whole process.

People

Technical Paper

Surface Power Diagrams for Knit Singularity Placement

9:40am - 9:50am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe present an algorithm for knit singularity placement that leverages a generalization of power diagrams to surfaces. By optimizing singularity positions in a global fashion, we achieve faster and more optimal placement, allowing for denser knit graphs. Our framework robustly produces helix-free knit graphs with a variety of user constraints.

People

William Batara Jeremiah Samosir

VARIANT3D

Megan Hofmann

Surface Reconstruction from Unoriented Points via Green’s 3rd Identity

Edward Chien

Boston University

Technical Paper

10:45am - 10:55am PDT Wednesday, 22 July 2026 Room 408 B

Research & Education

Artificial Intelligence/Machine Learning

Generative AI

Geometry

Modeling

Rendering

Simulation

Full Conference Supporter

Full Conference

DescriptionG3R reconstructs surfaces from unoriented point clouds by using Green's 3rd identity to recover globally consistent normals by solving a well-conditioned linear system. It removes the tangential nullspace that weakens prior winding-number-based methods and delivers accurate orientations and higher-quality reconstructions.

People

Zhonghao Wu

Shanghai Innovation Institute

Dong Xiao

Renjie Chen

Sustainable Research in Computer Graphics

Birds of a Feather

5:00pm - 6:00pm PDT Tuesday, 21 July 2026 Room 512

Research & Education

Ethics and Society

Full Conference Supporter

Full Conference

Experience

DescriptionFrom climate change to biodiversity loss and resource exhaustion, human activities are impacting Earth’s limits and Computer Graphics is no exception. How can our research practices and organizations evolve to respect these limits?

After the success of last year’s BoF, we continue building a community of people who want to think about the broader impacts of our research and how to collectively work towards a more sustainable future.

This interactive meetup session will allow attendees to share experiences and questions on related topics in small groups, regardless of their current levels of involvement or expertise in sustainable approaches to research.

People

Ruben Wiersma

Chenxi Liu

Emilie Yu

SWOT Mission Unlocks a New View of Our Waterways

Computer Animation Festival

Susurros

12:45pm - 1:45pm PDT Tuesday, 21 July 2026 411 Theatre

Full Conference Supporter

Full Conference

DescriptionFrom the witch hunts of 17th-century Europe to the overturning of Roe v. Wade in the United States in 2022, Susurros follows the story of two women faced with a pregnancy they did not choose. Separated by four centuries, Maria and Adeleida see their destinies echo each other inevitably. In the shadow of obscurantism, history repeats itself.

People

Director

Director

Director

Director

Director

Director

Computer Animation Festival

6:30pm - 8:30pm PDT Monday, 20 July 2026 Hall K

DescriptionThis data visualization shows the first ever global survey of changes in river volume over the course of a year. River volume is the how much water flows through a channel per unit time (e.g., cubic meters per second). The data show monthly river volume anomalies which is the difference from normal volume values. In this visualization, color and river thickness are driven by volume anomalies. Background land data are also monthly, capturing seasonal changes in land color and the advance and retreat of snow cover. A strong correlation between river volume and seasonality is evident throughout.

These observed data are from the Surface Water and Ocean Topography (SWOT) spacecraft. SWOT is a joint mission between NASA and the French space agency (CNES). SWOT's primary goal is to make the first global survey of Earth's surface water, including oceans, lakes, rivers, and reservoirs.

People

Gregory Shirah

Director, Visualizer

NASA/GSFC

Scientific Visualization Studio

Grace Denny

Sr. Specialist, Television Production, Video Producer for NASA Earth Science

NASA/GSFC

Technical Paper

SymX: Energy-based Simulation from Symbolic Expressions

11:45am - 11:55am PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Animation

Modeling

Simulation

Full Conference Supporter

Full Conference

DescriptionSymX is an open-source framework that turns succinct symbolic energy expressions into optimized code, delivering automatic first- and second-order derivatives and parallel assembly for Newton-style optimization time integrators. SymX facilitates building complex simulations, including high-order FEM, rigid-deformable coupling, and frictional contact, accelerating simulation research.

People

José Fernández-Fernández

Fabian Löschner

Lukas Westhofen

Andreas Longva

Jan Bender

José Fernández-Fernández

IASLab (Interactive Arts & Science Lab) - La Salle Barcelona (Universitat Ramon Llull)

Spatial Storytelling

SYNAPTICON

2:00pm - 2:45pm PDT Thursday, 23 July 2026 Concourse Hall

Gaming & Interactive

Artificial Intelligence/Machine Learning

Ethics and Society

Spatial Computing

Full Conference Supporter

Full Conference

Experience

DescriptionSYNAPTICON is an artistic research artifact at the intersection of neuro-hacking, brain-computer interfaces (BCIs), and foundation models, probing new territories of human expression, aesthetics, and AI alignment.

People

Albert Barque-Duran

Technical Paper

Synchronizing Fields with Singularities

9:10am - 9:20am PDT Thursday, 23 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Fabrication

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionWe cast a variety of field-processing problems into the language of synchronization, unlocking a unified algorithm based on semidefinite relaxation. Our method produces better optima, enables new boundary conditions, and comes with a geometric interpretation in terms of lifting topological defects (singularities).

People

Natalia Pacheco-Tallaj

Taiwan Night (a.k.a. the Taipei SIGGRAPH Reunion)

Birds of a Feather

9:15pm - 11:59pm PDT Sunday, 19 July 2026 Prank Bar

Arts & Design

Gaming & Interactive

New Technologies

Production & Animation

Research & Education

Animation

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Chapters

Computer Vision

Digital Twins

Display

Diversity, Equity and Inclusion

Dynamics

Education

Ethics and Society

Fabrication

Games

Generative AI

Geometry

Graphics Systems Architecture

Haptics

Hardware

History

Image Processing

Industry Insight

Lighting

Math Foundations and Theory

Modeling

Networking

Performance

Physical AI

Pioneers

Pipeline Tools and Work

Real-Time

Rendering

Robotics

Scientific Visualization

Simulation

Spatial Computing

Virtual Reality

Visual Effects

Full Conference Supporter

Full Conference

Experience

DescriptionTaiwan Night (a.k.a. the Taipei ACM SIGGRAPH Chapter Reunion) is an informal gathering for researchers, artists, designers, students, and professionals interested in Taiwan's computer graphics, XR, AI, digital art, and creative technology communities. Supported by Taipei ACM SIGGRAPH, it's a chance to connect with Taiwanese colleagues, exchange ideas, and learn about developments from academia, industry, and startups. All are welcome.

Join us at Prank Bar (1100 S Hope St, Los Angeles, CA 90015), starting at 21:15 (PT) for RSVP'd guests and open to everyone after 23:00 (PT).

People

Bing-Yu Chen

Yu-Lun Liu

Taming optimization variance in compact neural shading networks

Technical Paper

2:20pm - 2:30pm PDT Wednesday, 22 July 2026 Room 408 A

Research & Education

Artificial Intelligence/Machine Learning

Lighting

Modeling

Real-Time

Rendering

Full Conference Supporter

Full Conference

DescriptionWe present a training strategy for small networks that improves stability, reducing run-to-run variance by 88% and average loss by 38%. Multiple instances train in parallel on different batch slices, while weaker ones are periodically removed until only the best-performing instance remains, improving reliability for neural shading models.

People

Educator's Forum

Teaching Building Game Engines: An entry-level course on game programming without pre-built Game Engines

9:20am - 9:40am PDT Tuesday, 21 July 2026 Room 501 ABC

Gaming & Interactive

Research & Education

Education

Games

Image Processing

Modeling

Real-Time

Full Conference Supporter

Full Conference

Experience

DescriptionIn this paper, we present our singular course on teaching fundamental game programming skills by building game engines from scratch. The course is designed to provide a pathway for students in game development as an entry level course, while providing students a pathway to learning industry specific technologies later on.

People

Michael Shah

Teaching OpenGL 4.5/4.6 in Introductory Computer Graphics: A Hidden Sweet Spot in Graphics API Education Accessibility

Educator's Forum

10:45am - 11:05am PDT Wednesday, 22 July 2026 Room 501 ABC

Gaming & Interactive

New Technologies

Research & Education

Augmented Reality

Digital Twins

Education

Games

Image Processing

Real-Time

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionIn this paper, I discuss my effort and philosophy on how to balance the tension of teaching beginners introductory computer graphics programming with the appropriate API. The solution I have found is by teaching OpenGL 4.5 as the minimum graphics API and and introducing Vulkan-like programming abstractions.

People

Michael Shah

Techspressionism: An Expressive Approach to Digital Art

Birds of a Feather

12:00pm - 1:00pm PDT Thursday, 23 July 2026 Room 510

Arts & Design

Gaming & Interactive

New Technologies

Animation

Art

Artificial Intelligence/Machine Learning

Image Processing

Scientific Visualization

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionTechspressionism: what is it? An artistic approach in which technology is utilized as a means to express emotional experience. Its practitioners form a global network of artists spanning over 45 countries. This presentation highlights current activities, including exhibitions at the LA Center for Digital Art (LACDA) and the Arda Khiva Museum in Uzbekistan, as well as past exhibitions and initiatives. We also discuss our monthly virtual salons, artist interviews, roundtables, and weekly coworking sessions. Additionally, we will share details about an exciting new collaboration between Techspressionism and SIGGRAPH DAC that is on display during SIGGRAPH2006.

People

Cynthia B. Rubin

C B Rubin Studio

Patrick Lichty

Winona State University

Gregory Patrick Garvey

Quinnipiac University

Randi Matushevitz

Independent Artist

Emerging Technologies

Telekinetic Drive: Controlling Robots with Intent-Leaking Micro-Motions

10:30am - 5:00pm PDT Monday, 20 July 2026 Concourse Hall

Arts & Design

Gaming & Interactive

New Technologies

Research & Education

Art

Artificial Intelligence/Machine Learning

Audio

Augmented Reality

Capture/Scanning

Computer Vision

Digital Twins

Display

Dynamics

Education

Fabrication

Games

Generative AI

Graphics Systems Architecture

Haptics

Hardware

Image Processing

Performance

Physical AI

Pipeline Tools and Work

Real-Time

Robotics

Scientific Visualization

Spatial Computing

Virtual Reality

Full Conference Supporter

Full Conference

Experience

DescriptionWe propose Telekinetic Drive, a robot control system which directly connects user intent to control output by utilizing bodily micro-motions that unconsciously leak out when the user intends to operate. Participants move a robot arm through mental effort without wearing any devices or explicitly moving their bodies for control.

People

Genki Akimoto

Shuto Takashita

Tomoya Sasaki

Tokyo University of Science

Hiroto Saito

Masahiko Inami

Tempo3D: Efficient Temporal-Aware Fine-Tuning and Multi-View Latent Aggregation for 3D Generation

Technical Paper

11:05am - 11:15am PDT Tuesday, 21 July 2026 Room 403 B

Research & Education

Artificial Intelligence/Machine Learning

Geometry

Modeling

Full Conference Supporter

Full Conference

DescriptionTempo3D is a resource-efficient framework for high-fidelity 3D generation from a single image. By innovatively enhancing detail learning and resolving single-view ambiguities without expensive retraining, it delivers state-of-the-art geometric fidelity. Additionally, Tempo3D empowers users with natural language-guided 3D editing.

People

Huizhi Zhu

School of Computer Science

Jiongming Qin

School of Computer Science

Yusen Wang

DFRD, Dongfeng Motor Corporation Research&Development Institute

Chunxia Xiao

School of Computer Science

Birds of a Feather

Textiles

11:00am - 1:00pm PDT Monday, 20 July 2026 Room 512

Research & Education

Fabrication

Modeling

Rendering

Robotics

Simulation

Full Conference Supporter

Full Conference

Experience

DescriptionTextiles are everywhere in graphics, from simulation and rendering to fabrication and robotics. Come to this Birds of a Feather to meet others interested in the unique challenges and opportunities textiles present to the graphics community. We'll talk about current state of the art techniques, what problems still need to be solved, and where research is going in the future. Cool demos are encouraged!

People

Jenny Lin

Free University of Bozen-Bolzano

Michael Haller

Gilbert Bernstein

James McCann

Adriana Schulz