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:20260805T205520Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260720T140000
DTEND;TZID=America/Los_Angeles:20260720T153000
UID:siggraph_SIGGRAPH 2026_sess109@linklings.com
SUMMARY:Faces & Avatars
DESCRIPTION:Topologically Consistent Multi-view 3D Head Reconstruction via
  Coarse-Guided Layered Surface Sampling\n\nFrom calibrated multi-view imag
 es, SHELLS reconstructs 18k-vertex 3D heads in 0.08 seconds. It aggregates
  DinoV2 features via projective surface-aware feature sampling, allowing a
  transformer to predict dense semantic meshes 3.5x faster with 88% less GP
 U memory than state-of-the-art methods. The res...\n\n\nTimo Bolkart, Daoy
 e Wang, and Prashanth Chandran (Google)\n---------------------\nEmotion Ma
 nipulation for Talking-Head Videos via Facial Landmarks\n\nPreserving lip 
 synchronization during emotion manipulation in video is a major challenge.
  This paper proposes a method using a pretrained StyleGAN and a latent-bas
 ed landmark editing module. It modifies the latent edit direction with fac
 ial landmarks, enabling fast, high-quality emotion changes whil...\n\n\nKw
 anggyoon Seo (Flawless AI); Rene Jotham Culaway (Burt Intelligence); Byeon
 gUk Lee (Amazon Robotics); Junyong Noh (KAIST, Visual Media Lab); and Kwan
 ggyoon Seo\n---------------------\nLearning a Delighting Prior for Facial 
 Appearance Capture in the Wild\n\nA high-quality facial appearance capture
  method from casual smartphone videos with a powerful delighting prior.\n\
 n\nYuxuan Han, Xin Ming, Tianxiao Li, and Zhuofan Shen (Tsinghua Universit
 y); Qixuan Zhang and Lan Xu (ShanghaiTech University); and Feng Xu (Tsingh
 ua University)\n---------------------\nBringing Diversity from Diffusion M
 odels to Semantic-Guided Face Asset Generation\n\nThis paper introduces a 
 framework for generating high-quality, semantically controllable facial as
 sets. By leveraging a diffusion model's diversity, we develop a face asset
  synthesis pipeline to produce paired albedo and geometry data with semant
 ic labels. These pairs are then used to train a disent...\n\n\nYunxuan Cai
 , Sitao Xiang, Zongjian Li, Haiwei Chen, and Yajie Zhao (University of Sou
 thern California  Institute for Creative Technologies) and Yunxuan Cai\n--
 -------------------\nEchoAvatar: Real-time Generative Avatar Animation fro
 m Audio Streams\n\nWe introduce a novel framework designed to generate con
 tinuous, coherent full-body motion from arbitrary audio streams with low l
 atency. Our approach is a unified streaming architecture capable of synthe
 sizing continuous motion from incremental audio inputs. And it serves as a
  plug-and-play solution...\n\n\nBohong Chen, Yumeng Li, Yinglin Xu, Youyi 
 Zheng, Yanlin Weng, and Kun Zhou (State Key Laboratory of CAD & CG, Zhejia
 ng University)\n---------------------\nSee-through: Single-image Layer Dec
 omposition for Anime Characters\n\nWe 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, seman
 tically distinct layers with inferred drawing orders — up to 19 layers inc
 luding hair, face, eyes, clothing...\n\n\nJian Lin and Chengze Li (Saint F
 rancis University); Haoyun Qin (University of Pennsylvania, Spellbrush / S
 hitagaki Lab); Kwun Wang Chan (Saint Francis University); Yanghua Jin (Spe
 llbrush); and Hanyuan Liu; Chun Wang, Stephen Choy; and Xueting Liu (Saint
  Francis University)\n---------------------\nFaces & Avatars - Interactive
  Discussion\n\nAfter 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 invite
 d to bring any material related to their paper that could instigate furthe
 r conversation such...\n\n\nInterest Area: Research & Education\n\nKeyword
 : Animation, Artificial Intelligence/Machine Learning, Generative AI, Geom
 etry, Modeling, Simulation\n\nRegistration Category: Full Conference Suppo
 rter, Full Conference\n\nSession Chair: Derek Bradley (Walt Disney Company
 , Switzerland)
END:VEVENT
END:VCALENDAR