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:20260805T205517Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260722T140000
DTEND;TZID=America/Los_Angeles:20260722T153000
UID:siggraph_SIGGRAPH 2026_sess111@linklings.com
SUMMARY:4D Humans
DESCRIPTION:Implicit Surface Compression -- with Good Old Discrete Cosine 
 Transform and Motion Compensation\n\nWe present a real-time 4D compression
  framework for volumetric capture using the Truncated Signed Distance Fiel
 d (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 w...\n\n\nTao Jin, Shengxi Wu, and
  Tianshu Huang (Carnegie Mellon University); Mallesham Dasari (Northeaster
 n University); Srinivasan Seshan (Carnegie Mellon University); and Anthony
  Rowe (Carnegie Mellon University, Bosch Research)\n---------------------\
 n4D Human-Scene Reconstruction from Low-Overlap Captures\n\nWe reconstruct
  dynamic 4D scenes with multiple people from just 4 sparse cameras with mi
 nimal overlap. Our method separately handles backgrounds using video gener
 ation and humans using body model priors, then harmonizes the result with 
 a temporally consistent enhancement step, achieving high-quality...\n\n\nM
 inhyuk Hwang, Sangmin Kim, Seunguk Do, Daneul Kim, and Jaesik Park (Seoul 
 National University)\n---------------------\nATGS: Anchored Temporal Gauss
 ian Splatting for Long Volumetric Video Representation\n\nATGS is a volume
 tric video reconstruction method that handles long sequences with complex 
 motions and supports rendering from arbitrary viewpoints, enabling immersi
 ve experiences.\n\n\nJiahao Wu and Jie Liang (School of Computer Science, 
 Peking University; Peking University, China); Die Hu (Peking University); 
 Jiayu Yang (Pengcheng Laboratory, Pengcheng lab); Kaiqiang Xiong (Peking U
 niversity; Peking University, China); Xiang Li (Pengcheng lab, Peking Univ
 ersity); Xiaoyun Zheng (Pengcheng Lab, Pengcheng lab); Chao Wang (Peng Che
 ng Lab; Peking University, China); and Ronggang Wang (Peking University, P
 engcheng lab)\n---------------------\nVFAvatar: Feed-Forward 3D Avatar Rec
 onstruction from Casual Image Collections\n\nWe introduce Visual-Fusion-Av
 atar (VFAvatar), a novel end-to-end feed-forward framework that reconstruc
 ts 3D avatars by fusing visual cues from casual image collections in just 
 a few seconds. \nVFAvatar integrates a pose-free reconstruction foundation
  model with a pretrained human generation prior in...\n\n\nShuo Huang, Zix
 uan Wang, Xiaoyu Qin, Shikun Sun, Jiayi Li, and Jia Jia (CS Dept, Tsinghua
  University)\n---------------------\nHigh-Fidelity 4D Cloth Capture Pipeli
 ne with a Two-Level Pattern\n\nWe present a 4D (spatio-temporal) cloth cap
 ture system and a two-level pattern that achieves 1mm spatial resolution u
 sing only 16 RGB cameras. Our method produces temporally coherent sequence
 s with no self penetration that faithfully capture fine wrinkles and folds
  even during complex motions with s...\n\n\nZiheng Liu (University of Utah
 ); Anka Chen (NVIDIA); and Shu Chen, Yin Yang, Cem Yuksel, and Jenny Lin (
 University of Utah)\n---------------------\n4D Humans - Interactive Discus
 sion\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 invited to br
 ing any material related to their paper that could instigate further conve
 rsation such...\n\n\nInterest Area: Research & Education\n\nKeyword: Anima
 tion, Artificial Intelligence/Machine Learning, Geometry, Modeling, Render
 ing, Simulation\n\nRegistration Category: Full Conference Supporter, Full 
 Conference\n\nSession Chair: Tamy Boubekeur (Adobe)
END:VEVENT
END:VCALENDAR