BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030430Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251216T163000
DTEND;TZID=Asia/Hong_Kong:20251216T173500
UID:siggraphasia_SIGGRAPH Asia 2025_sess131@linklings.com
SUMMARY:It's All About the Motion
DESCRIPTION:The Technical Papers program is the heartbeat of SIGGRAPH Asia
 , spotlighting world-class scholarly research at the forefront of computer
  graphics and interactive techniques. For decades, it has been the definit
 ive venue where bold ideas take root, foundational concepts are reimagined
 , and the future of visual computing is shaped.\n\nThis year, we explore n
 ew intersections of algorithms and artistry, automation and authorship, to
 ols and imagination – challenging the very way we design, simulate, visual
 ize, and interact with digital worlds.\n\nCurvature Enthusiasm: Correspond
 ence-Free Interpolation and Matching of Articulated 3D Shapes using Compre
 ssed Normal Cycles\n\nWe present an unsupervised framework for physically 
 plausible shape interpolation and dense correspondence estimation between 
 3D articulated shapes. Our method uses Neural Ordinary Differential Equati
 ons to generate smooth flow fields that define diffeomorphic transformatio
 ns, ensuring topological c...\n\n\nAdam Hartshorne, Allen Paul, and Tony S
 hardlow (University of Bath) and Neill D. F. Campbell (University College 
 London (UCL), University of Bath)\n---------------------\nControl Operator
 s for Interactive Character Animation\n\nNeural-network-based character co
 ntrollers are increasingly common and capable. However, the integration of
  desired control inputs such as joystick movement, motion paths, and objec
 ts in the environment, remains challenging. This is because these inputs o
 ften require custom feature engineering, spec...\n\n\nRuiyu Gou (Epic Game
 s), Michiel van de Panne (University of British Columbia), and Daniel Hold
 en (Epic Games)\n---------------------\nLearning to Ball: Composing Polici
 es for Long-Horizon Basketball Moves\n\nLearning a control policy for a mu
 lti-phase, long-horizon task, such as basketball maneuvers, remains challe
 nging for reinforcement learning approaches due to the need for seamless p
 olicy composition and transitions between skills. A long-horizon task typi
 cally consists of distinct subtasks with wel...\n\n\nPei Xu, Zhen Wu, Ruoc
 heng Wang, Vishnu Sarukkai, and Kayvon Fatahalian (Stanford University); I
 oannis Karamouzas (University of California Riverside); Victor Zordan (Rob
 lox); and C. Karen Liu (Stanford University)\n---------------------\nStabl
 eMotion: Training Motion Cleanup Models with Unpaired Corrupted Data\n\nMo
 tion capture (mocap) data often exhibits visually jarring artifacts due to
  inaccurate sensors and post-processing. Cleaning this corrupted data can 
 require substantial manual effort from human experts, which can be a costl
 y and time-consuming process. Previous data-driven motion cleanup methods 
 of...\n\n\nYuxuan Mu (Simon Fraser University); Hung Yu Ling (Electronic A
 rts); Yi Shi (Simon Fraser University); Ismael Baira Ojeda (Electronic Art
 s); Pengcheng Xi and Chang Shu (National Research Council Canada); Fabio Z
 inno (Electronic Arts); and Xue Bin Peng (Simon Fraser University, NVIDIA)
 \n---------------------\nMotion In-Betweening for Densely Interacting Char
 acters\n\nMotion in-betweening is the problem to synthesize movement betwe
 en keyposes. Traditional research focused primarily on single characters. 
 Extending them to densely interacting characters is highly challenging, as
  it demands precise spatial-temporal correspondence between the characters
  to maintain t...\n\n\nXiaotang Zhang and Ziyi Chang (Durham University), 
 Qianhui Men (University of Bristol), and Hubert Shum (Durham University)\n
 ---------------------\nEnvironment-aware Motion Matching\n\nInteractive ap
 plications demand believable character animation that responds naturally t
 o dynamic environments. Traditional animation techniques often struggle to
  handle arbitrary situations, leading to a growing trend of dynamically se
 lecting motion-captured animations based on predefined features....\n\n\nJ
 ose Luis Ponton (Universitat Politècnica de Catalunya), Sheldon Andrews (É
 cole de technologie supérieure (ÉTS)), and Carlos Andujar and Nuria Pelech
 ano (Universitat Politècnica de Catalunya)\n\nRegistration Category: Full 
 Access, Full Access Supporter\n\nSession Chair: Jungdam Won (Seoul Nationa
 l University)
END:VEVENT
END:VCALENDAR