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:20260805T205601Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260723T141000
DTEND;TZID=America/Los_Angeles:20260723T142000
UID:siggraph_SIGGRAPH 2026_sess105_papers_934@linklings.com
SUMMARY:TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Vi
 deo-to-Animation
DESCRIPTION:Chengfeng Pu, Jia-Peng Zhang, and Meng-Hao Guo (CS Dept, Tsing
 hua University); Yan-Pei Cao (VAST); and Shi-Min Hu (CS Dept, Tsinghua Uni
 versity)\n\nTopoCap is a unified framework for motion capture and retarget
 ing from monocular video, supporting arbitrary skeletal topologies without
  test-time optimization. Leveraging a two-stage generative pipeline, TopoC
 ap achieves motion transfer across diverse creatures, backed by Mobjaverse
 —a dataset with over 5,000 skeletal topologies and 2 million frames for ro
 bust zero-shot retargeting.\n\nInterest Area: Research & Education\n\nKeyw
 ord: Animation, Artificial Intelligence/Machine Learning, Modeling, Simula
 tion\n\nRegistration Category: Full Conference Supporter, Full Conference\
 n\nSession Chair: Min Lu (Shenzhen University (SZU))\n\n
END:VEVENT
END:VCALENDAR