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:20251218T030516Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251215T163000
DTEND;TZID=Asia/Hong_Kong:20251215T173500
UID:siggraphasia_SIGGRAPH Asia 2025_sess115@linklings.com
SUMMARY:Physically Based Simulation & Dynamic Environments
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\nCFC: Simulating Character-Fluid 
 Coupling using a Two-Level World Model\n\nHumans possess the ability to ma
 ster a wide range of motor skills, using which they can quickly and flexib
 ly adapt to the surrounding environment. Despite recent progress in replic
 ating such versatile human motor skills, existing research often oversimpl
 ifies or inadequately captures the complex int...\n\n\nZhiyang Dou and Che
 n Peng (The University of Hong Kong), Xinyu Lu (Centre for Transformative 
 Garment Production), Xiaohan Ye (University of Hong Kong), Lixing Fang (Un
 iversity of Massachusetts Amherst), Yuan Liu (HKUST), Wenping Wang (Texas 
 A&M University), Chuang Gan (University of Massachusetts Amherst), Lingjie
  Liu (University of Pennsylvania), and Taku Komura (The University of Hong
  Kong)\n---------------------\nFreeMusco: Motion-Free Learning of Latent C
 ontrol for Morphology-Adaptive Locomotion in Musculoskeletal Characters\n\
 nWe propose FreeMusco, a motion-free framework that jointly learns latent 
 representations and control policies for musculoskeletal characters. By le
 veraging the musculoskeletal model as a strong prior, our method enables e
 nergy-aware and morphology-adaptive locomotion to emerge without motion da
 ta. T...\n\n\nMinkwan Kim and Yoonsang Lee (Hanyang University)\n---------
 ------------\nFast & Stable Control of Coupled Solid-Fluid Dynamic Systems
 \n\nWe propose a Reinforcement Learning (RL) algorithm that combines sever
 al novel techniques to achieve more stable and robust control results for 
 coupled solid-fluid systems. Our method utilizes the twin-delayed actor-cr
 itic algorithm to efficiently utilize off-policy data and achieve faster c
 onvergen...\n\n\nJie Chen (VCIP, College of Computer Science, Nankai Unive
 rsity); Zherong Pan (LIGHTSPEED); and Bo Ren (VCIP, College of Computer Sc
 ience, Nankai University)\n---------------------\nForce-Dual Modes: Subspa
 ce Design from Stochastic Forces\n\nWe generate subspaces from force distr
 ibutions, allowing us to carry out force simulations in many regimes of ac
 tuations. The dragon above is composed of spring muscles that lend themsel
 ves to multiple types of motion, including walking, flapping it's wings, o
 r wagging its tail. A user can interacti...\n\n\nOtman Benchekroun and Eit
 an Grinspun (University of Toronto) and Maurizio Chiaramonte and Philip Al
 len Etter (Meta)\n---------------------\nPhySIC: Physically Plausible 3D H
 uman-Scene Interaction and Contact from a Single Image\n\nReconstructing m
 etrically accurate humans and their surrounding scenes from a single image
  is crucial for virtual reality, robotics, and comprehensive 3D scene unde
 rstanding. However, existing methods struggle with depth ambiguity, occlus
 ions, and physically inconsistent contacts. To address these c...\n\n\nPra
 dyumna Yalandur-Muralidhar and Yuxuan Xue (University of Tuebingen); Xiang
 hui Xie (University of Tuebingen, Max Planck Institute for Informatics); M
 argaret Kostyrko (University of Tuebingen); and Gerard Pons-Moll (Universi
 ty of Tuebingen, Max Planck Institute for Informatics)\n------------------
 ---\nA Highly-Efficient Hybrid Simulation System for Flight Controller Des
 ign and Evaluation of Unmanned Aerial Vehicles\n\nUnmanned aerial vehicles
  (UAVs) have demonstrated remarkable efficacy across diverse fields. \nNev
 ertheless, developing flight controllers tailored to a specific UAV design
 , particularly in environments with strong fluid-interactive dynamics, rem
 ains challenging. Conventional controller design experi...\n\n\nJiwei Wang
 , Wenbin Song, Yicheng Fan, Yang Wang, and Xiaopei Liu (ShanghaiTech Unive
 rsity)\n\nRegistration Category: Full Access, Full Access Supporter\n\nSes
 sion Chair: Bo Ren (TMCC, College of Computer Science, Nankai University)
END:VEVENT
END:VCALENDAR