BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260805T205507Z
LOCATION:Room 403  B
DTSTART;TZID=America/Los_Angeles:20260721T090000
DTEND;TZID=America/Los_Angeles:20260721T103000
UID:siggraph_SIGGRAPH 2026_sess112@linklings.com
SUMMARY:Generative 3D (2)
DESCRIPTION:SegviGen: Repurposing 3D Generative Model for Part Segmentatio
 n\n\nSegviGen is a framework for 3D part segmentation which unifies three 
 settings in one architecture: interactive part segmentation, full segmenta
 tion, and 2D segmentation map–guided full segmentation. It improves over s
 ota by 40% on interactive segmentation and by 15% on full segmentation, wh
 ile...\n\n\nLin Li (Renmin University of China); Haoran Feng (Tsinghua Uni
 versity); Zehuan Huang and Haohua Chen (Beihang University); Wenbo Nie (Be
 ijing Jiaotong University); Shaohua Hou, Keqing Fan, and Pan Hu (Beihang U
 niversity); Sheng Wang and Buyu Li (Bambu Lab); and Lu Sheng (Beihang Univ
 ersity)\n---------------------\nSimArt: Decomposing Monolithic Meshes into
  Sim-ready Articulated Assets via MLLM\n\nSIMART is a unified multimodal l
 arge language model framework that converts static 3D meshes into simulati
 on-ready articulated assets. By jointly modeling part decomposition and ki
 nematics with a sparse 3D VQ-VAE, it reduces token complexity and enables 
 scalable, high-fidelity object generation for ...\n\n\nChuanrui Zhang (Nan
 yang Technological University, Singapore); Minghan Qin, Yuang Wang, Baifen
 g Xie, and Hang Li (ByteDance Seed); and Ziwei Wang (Nanyang Technological
  University, Singapore)\n---------------------\nNeural Cellular Automata: 
 From Cells to Pixels\n\nWe pair Neural Cellular Automata with a lightweigh
 t 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 text
 ures and grows morphologies ...\n\n\nEhsan Pajouheshgar, Yitao Xu, and Ali
  Abbasi (EPFL); Alexander Mordvintsev (Google Research); and Wenzel Jakob 
 and Sabine Süsstrunk (EPFL)\n---------------------\nNeural Particle Automa
 ta: Learning Self-Organizing Particle Dynamics\n\nNeural Particle Automata
  extend Neural Cellular Automata from fixed grids to dynamic particles. Ea
 ch particle carries a continuous position and internal state, updated by a
  shared neural rule with SPH-based local perception. Backed by optimized C
 UDA kernels, NPA learn scalable self-organizing dynami...\n\n\nEhsan Pajou
 heshgar (EPFL), Hyunsoo Kim (Korea Advanced Institute of Science and Techn
 ology (KAIST)), Sabine Süsstrunk and Wenzel Jakob (EPFL), and Jinah Park (
 Korea Advanced Institute of Science and Technology (KAIST))\n-------------
 --------\nPixTex: Consistent 3D Texturing via Pixel-Space Multi-View Diffu
 sion\n\nWe propose PixTex, the first pixel-space multi-view diffusion fram
 ework for texture generation. By bypassing latent compression and utilizin
 g a coarse-to-fine strategy, it ensures lossless geometric guidance and su
 perior pixel-level multi-view consistency, achieving state-of-the-art, hig
 h-fidelity, ...\n\n\nYuqing Zhang (State Key Lab of CAD&CG, Zhejiang); Yan
 -Pei Cao (VAST); Hao Xu, Yiqian Wu, Sirui Lin, and Yuqing Wang (State Key 
 Lab of CAD&CG, Zhejiang University); Ding Liang and Yuan-Chen Guo (VAST); 
 and Xiaogang Jin (Zhejiang University; State Key Laboratory of CAD&CG, Zhe
 jiang University)\n---------------------\nGenerative 3D Gaussians with Lea
 rned Density Control\n\nDeG is an image-to-3D generative framework for Gau
 ssian 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, hig
 h-quality 3D asset gen...\n\n\nRunjie Yan (Institute for Interdisciplinary
  Information Sciences, Tsinghua University; VAST) and Yan-Pei Cao, Peng Wa
 ng, Ding Liang, and Yuan-Chen Guo (VAST)\n---------------------\nGenerativ
 e 3D (2) - Interactive Discussion\n\nAfter the summary presentations, atte
 ndees will participate in an interactive discussion. Outside the room will
  be a series of poster boards for authors to gather around with the audien
 ce. Authors are invited to bring any material related to their paper that 
 could instigate further conversation such...\n\n\nInterest Area: Research 
 & Education\n\nKeyword: Artificial Intelligence/Machine Learning, Geometry
 , Modeling, Rendering, Robotics\n\nRegistration Category: Full Conference 
 Supporter, Full Conference\n\nSession Chair: Qixing Huang (University of T
 exas Austin)
END:VEVENT
END:VCALENDAR