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:20260417T190050Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250814T104500
DTEND;TZID=America/Los_Angeles:20250814T121500
UID:siggraph_SIGGRAPH 2025_sess111@linklings.com
SUMMARY:Loco/Motion Capture
DESCRIPTION:HumanRAM: Feed-forward Human Reconstruction and Animation Mode
 l using Transformers\n\nExisting avatar methods typically require sophisti
 cated dense-view capture and/or time-consuming per-subject optimization pr
 ocesses. HumanRAM proposes a feed-forward approach for generalizable human
  reconstruction and animation from monocular or sparse human images. Exper
 iments show that HumanRAM ac...\n\n\nZhiyuan Yu (Department of Mathematics
 , Hong Kong University of Science and Technology); Zhe Li (Huawei); Hujun 
 Bao (State Key Laboratory of CAD&CG, Zhejiang University); Can Yang (Depar
 tment of Mathematics, Hong Kong University of Science and Technology); and
  Xiaowei Zhou (State Key Laboratory of CAD&CG, Zhejiang Univerisity)\n----
 -----------------\nInverse Geometric Locomotion\n\nWe present a computatio
 nal framework for optimizing shape sequences to achieve user-defined motio
 n objectives in deformable bodies undergoing geometric locomotion. Through
  a reduced spatiotemporal parameterization of the shape sequences, our met
 hod is able to efficiently capture the complex coupling...\n\n\nQuentin Be
 cker (EPFL); Oliver Gross (University of California San Diego, EPFL); and 
 Mark Pauly (EPFL)\n---------------------\nLoco/Motion Capture - Interactiv
 e Discussion\n\nAfter the summary presentations, attendees will participat
 e in an interactive discussion. Outside the room will be a series of poste
 r boards for authors to gather around with the audience. Authors are invit
 ed to bring any material related to their paper that could instigate furth
 er conversation such...\n\n---------------------\nEncoded Marker Clusters 
 for Auto-Labeling in Optical Motion Capture\n\nMarker-based optical motion
  capture (MoCap) is critical for virtual production and movement sciences.
  We propose a novel framework for MoCap auto-labeling and matching using u
 niquely coded clusters of reflective markers (AEMCs). Compared to commerci
 al software, our method achieves higher labeling ac...\n\n\nHao Wang (Beih
 ang University, Beijing Jiaotong University); Taogang Hou, Tianhui Liu, an
 d Jiaxin Li (Beijing Jiaotong University); Tianmiao Wang (Beihang Universi
 ty); and Hao Wang and Taogang Hou\n---------------------\nElastic Locomoti
 on with Mixed Second-order Differentiation\n\nOur framework enables realis
 tic and interesting elastic body locomotion by determining optimal muscle 
 activations to achieve desired movements. It combines interior-point metho
 d for contact modeling with a novel mixed second-order differentiation alg
 orithm that merges analytic and numerical approach...\n\n\nSiyuan Shen, Ti
 anjia Shao, and Kun Zhou (Zhejiang University); Chenfanfu Jiang (UCLA); Sh
 eldon Andrews (École de Technologie Supérieure (ÉTS)); Victor Zordan (Robl
 ox); and Yin Yang (University of Utah)\n---------------------\nImproving G
 lobal Motion Estimation in Sparse IMU-based Motion Capture with Physics\n\
 nWe propose a physics-driven approach to IMU-based motion capture, improvi
 ng global motion estimation with 3D contact modeling and gravity awareness
 . Our method estimates world-aligned 3D motion, contact points, contact fo
 rces, joint torques, and proxy surface interactions using only six IMUs in
  real...\n\n\nXinyu Yi, Shaohua Pan, and Feng Xu (Tsinghua University)\n--
 -------------------\nDAMO: A Deep Solver for Arbitrary Marker Configuratio
 n in Optical Motion Capture\n\nThis paper introduces DAMO, a Deep solver f
 or Arbitrary Marker configuration in Optical motion capture. DAMO directly
  infers the relationship between each raw marker point and 3D model joint,
  without using predefined marker labels and configuration information.\n\n
 \nKyeongMin Kim and SeungWon Seo (Korea University), DongHeun Han (KyungHe
 e University), HyeongYeop Kang (Korea University), and KyeongMin Kim\n\nIn
 terest Area: Research & Education\n\nRecording: Livestreamed, Not Livestre
 amed, Recorded, Not Recorded\n\nRegistration Category: Full Conference, Vi
 rtual Access, Thursday\n\nSession Chair: David Hahn (Technische Universitä
 t Wien (TU Wien))
END:VEVENT
END:VCALENDAR