BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070312Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T154000
DTEND;TZID=Australia/Melbourne:20231215T163500
UID:siggraphasia_SIGGRAPH Asia 2023_sess139@linklings.com
SUMMARY:Motion Capture and Reconstruction
DESCRIPTION:Technical Papers\n\nA Locality-based Neural Solver for Optical
  Motion Capture\n\nWe present a novel locality-based learning method for c
 leaning and solving optical motion capture data. Given noisy marker data, 
 we propose a new heterogeneous graph neural network which treats markers a
 nd joints as different types of nodes, and uses graph convolution operatio
 ns to extract the local...\n\n\nXiaoyu Pan and Bowen Zheng (State Key Labo
 ratory of CAD & CG, Zhejiang University; ZJU-Tencent Game and Intelligent 
 Graphics Innovation Technology Joint Lab); Xinwei Jiang, Guanglong Xu, Xia
 nli Gu, and Jingxiang Li (Tencent Games Digital Content Technology Center)
 ; Qilong Kou (Tencent Technology (Shenzhen) Co., LTD); He Wang (University
  College London (UCL)); Tianjia Shao and Kun Zhou (State Key Laboratory of
  CAD & CG, Zhejiang University); and Xiaogang Jin (State Key Laboratory of
  CAD & CG, Zhejiang University; ZJU-Tencent Game and Intelligent Graphics 
 Innovation Technology Joint Lab)\n---------------------\nReconstructing Cl
 ose Human Interaction from Multiple Views\n\nThis paper addresses the chal
 lenging task of reconstructing the poses of multiple individuals engaged i
 n close interactions, captured by multiple calibrated cameras. The difficu
 lty arises from the noisy or false 2D keypoint detection due to inter-pers
 on occlusion, the heavy ambiguity to associate ke...\n\n\nQing Shuai (Zhej
 iang University); Zhiyuan Yu (Department of Mathematics, Hong Kong Univers
 ity of Science and Technology); Zhize Zhou (Capital University of Physical
  Education and Sports); Lixin Fan and Haijun Yang (WeBank); Can Yang (Depa
 rtment of Mathematics, Hong Kong University of Science and Technology); an
 d Xiaowei Zhou (State Key Laboratory of CAD&CG, Zhejiang Univerisity)\n---
 ------------------\nFusing Monocular Images and Sparse IMU Signals for Rea
 l-time Human Motion Capture\n\nEither RGB images or inertial signals have 
 been used for the task of motion capture (mocap), but combining them toget
 her is a new and interesting topic. We believe that the combination is com
 plementary and able to solve the inherent difficulties of using one modali
 ty input, including occlusions, ext...\n\n\nShaohua Pan, Qi Ma, and Xinyu 
 Yi (Tsinghua University); Weifeng Hu, Xiong Wang, Xingkang ZHOU, and Jijun
 nan LI (OPPO Research Institute); and Feng Xu (Tsinghua University)\n-----
 ----------------\nAdaptive Tracking of a Single-Rigid-Body Character in Va
 rious Environments\n\nSince the introduction of DeepMimic [Peng et al. 201
 8], subsequent research\nhas focused on expanding the repertoire of simula
 ted motions across various\nscenarios. In this study, we propose an altern
 ative approach for this goal,\na deep reinforcement learning method based 
 on the simulation of a single...\n\n\nTaesoo Kwon, Taehong Gu, Jaewon Ahn,
  and Yoonsang Lee (Hanyang University)\n---------------------\nEfficient H
 uman Motion Reconstruction from Monocular Videos with Physical Consistency
  Loss\n\nVision-only motion reconstruction from monocular videos often pro
 duces artifacts such as foot sliding and jittery motions. Existing physics
 -based methods typically either simplify the problem to focus solely on fe
 et-ground contacts, or reconstruct full-body contacts within a physics sim
 ulator, neces...\n\n\nLin Cong and Philipp Ruppel (Universität Hamburg), Y
 izhou Wang (Peking University), Xiang Pan (Diago Tech Company), and Norman
  Hendrich and Jianwei Zhang (Universität Hamburg)\n\nRegistration Category
 : Full Access\n\nSession Chair: Yuting Ye (Reality Labs Research, Meta)
END:VEVENT
END:VCALENDAR