BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023313Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241206T144500
DTEND;TZID=Asia/Tokyo:20241206T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess150@linklings.com
SUMMARY:Hand and Human
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\n360-degree Human Video Generation with 4D Diffusion Transformer\n\nWe 
 present a novel approach for generating 360-degree high-quality, spatio-te
 mporally coherent human videos from a single image. Our framework combines
  the strengths of diffusion transformers for capturing global correlations
  across viewpoints and time, and CNNs for accurate condition injection. Th
 e...\n\n\nRuizhi Shao, Youxin Pang, Zerong Zheng, Jingxiang Sun, and Yebin
  Liu (Tsinghua University)\n---------------------\nPuzzleAvatar: Assemblin
 g 3D Avatars from Personal Albums\n\nGenerating personalized 3D avatars is
  crucial for AR/VR. However, recent text-to-3D methods that generate avata
 rs for celebrities or fictional characters, struggle with everyday people.
  Methods for faithful reconstruction typically require full-body images in
  controlled settings. What if a user coul...\n\n\nYuliang Xiu (Max Planck 
 Institute for Intelligent Systems); Yufei Ye (Carnegie Mellon University);
  Zhen Liu (Max Planck Institute for Intelligent Systems; Mila, Université 
 de Montréal); Dimitris Tzionas (University of Amsterdam); and Michael J. B
 lack (Max Planck Institute for Intelligent Systems)\n---------------------
 \nDiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Text
 ual Descriptions\n\nWe introduce DiffH2O, a new diffusion-based framework 
 for synthesizing realistic, dexterous hand-object interactions from natura
 l language. Our model employs a temporal two-stage diffusion process, divi
 ding hand-object motion generation into grasping and interaction stages to
  enhance generalization ...\n\n\nSammy Christen (ETH, Meta) and Shreyas Ha
 mpali, Fadime Sener, Edoardo Remelli, Tomas Hodan, Eric Sauser, Shugao Ma,
  and Bugra Tekin (Meta)\n---------------------\nMeasuring Human Motion Und
 er Clothing\n\nIn many applications involving clothing, it is essential to
  know how clothes move relative to the body hidden beneath. This is imposs
 ible using traditional optical motion capture methods due to visual occlus
 ion due to clothes and other body parts, and very difficult using previous
  non-optical method...\n\n\nLuis Bolanos, Pearson Wyder-Hodge, and Xindong
  Lin (University of British Columbia) and Dinesh K. Pai (University of Bri
 tish Columbia, Vital Mechanics Research)\n---------------------\nSynchroni
 ze Dual Hands for Physics-Based Dexterous Guitar Playing\n\nWe present a n
 ovel approach to synthesize dexterous motions for physically simulated han
 ds in tasks that require coordination between the control of two hands wit
 h high temporal precision. Instead of directly learning a joint policy to 
 control two hands, our approach performs bimanual control throug...\n\n\nP
 ei Xu and Ruocheng Wang (Stanford University)\n---------------------\nWorl
 d-Grounded Human Motion Recovery via Gravity-View Coordinates\n\nWe presen
 t a novel method for recovering world-grounded human motion from monocular
  video. The main challenge lies in the ambiguity of defining the world coo
 rdinate system, which varies between sequences. Previous approaches attemp
 t to alleviate this issue by predicting relative motion in an autoreg...\n
 \n\nZehong Shen, Huaijin Pi, Yan Xia, Zhi Cen, and Sida Peng (State Key La
 boratory of CAD&CG, Zhejiang University); Zechen Hu (Deep Glint); Hujun Ba
 o (State Key Laboratory of CAD&CG, Zhejiang University); Ruizhen Hu (Shenz
 hen University (SZU)); and Xiaowei Zhou (State Key Laboratory of CAD&CG, Z
 hejiang University)\n\nRegistration Category: Full Access, Full Access Sup
 porter\n\nLanguage Format: English Language\n\nSession Chair: Li-Yi Wei (A
 dobe Research)
END:VEVENT
END:VCALENDAR