BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T144500
DTEND;TZID=Asia/Tokyo:20241204T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess120@linklings.com
SUMMARY:Domo Arigato, Mr. Roboto /  Robots and Characters
DESCRIPTION:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nRobot Motion Diffusion Model: Motion Generation for Robotic Characters
 \n\nRecent advancements in generative motion models have achieved remarkab
 le results, enabling the synthesis of lifelike human motions from textual 
 descriptions. These kinematic approaches, while visually appealing, often 
 produce motions that fail to adhere to physical constraints, resulting in 
 artifact...\n\n\nAgon Serifi (ETH Zürich, Disney Research); Ruben Grandia 
 and Espen Knoop (Disney Research); Markus Gross (ETH Zürich, Disney Resear
 ch); and Moritz Bächer (Disney Research)\n---------------------\nActuators
  A La Mode: Modal Actuations for Soft Body Locomotion\n\nTraditional chara
 cter animation specializes in characters with a rigidly articulated skelet
 on and a bipedal/quadripedal morphology. This assumption simplifies many a
 spects for designing physically based animations, like locomotion, but com
 es with the price of excluding characters of arbitrary deform...\n\n\nOtma
 n Benchekroun (University of Toronto); Kaixiang Xie (McGill University); H
 sueh-Ti Derek Liu (Roblox); Eitan Grinspun (University of Toronto); Sheldo
 n Andrews (Ecole de Technologie Superieure, Roblox); and Victor Zordan (Ro
 blox)\n---------------------\nPC-Planner: Physics-Constrained Self-Supervi
 sed Learning for Robust Neural Motion Planning with Shape-Aware Distance F
 unction\n\nMotion Planning (MP) is a critical challenge in robotics, espec
 ially pertinent with the burgeoning interest in embodied artificial intell
 igence. Traditional MP methods often struggle with high-dimensional comple
 xities. Recently neural motion planners, particularly physics-informed neu
 ral planners ba...\n\n\nXujie Shen, Haocheng Peng, and Zesong Yang (State 
 Key Laboratory of CAD&CG, Zhejiang University); Juzhan Xu (Shenzhen Univer
 sity (SZU)); Hujun Bao (State Key Laboratory of CAD&CG, Zhejiang Universit
 y); Ruizhen Hu (Shenzhen University (SZU)); and Zhaopeng Cui (State Key La
 boratory of CAD&CG, Zhejiang University)\n---------------------\nMaskedMim
 ic: Unified Physics-Based Character Control Through Masked Motion Inpainti
 ng\n\nCrafting a single, versatile physics-based controller that can breat
 he life into interactive characters across a wide spectrum of scenarios re
 presents an exciting frontier in character animation. An ideal controller 
 should support diverse control modalities, such as sparse target keyframes
 , text ins...\n\n\nChen Tessler (NVIDIA Research), Yunrong Guo (NVIDIA), O
 fir Nabati and Gal Chechik (NVIDIA Research), and Xue Bin Peng (NVIDIA)\n-
 --------------------\nA Plentoptic 3D Vision System\n\nWe present a novel 
 multi-camera, multi-modal vision system designed for industrial robotics a
 pplications. The system generates high-quality 3D point clouds, with a foc
 us on improving the completeness and reducing hallucinations for collision
  avoidance across various geometries, materials, and lighti...\n\n\nAgasty
 a Kalra, Vage Tamaazyan, Alberto Dall'olio, Raghav Khanna, Tomas Gerlich, 
 Georgia Giannopolou, Guy Stoppi, Daniel Baxter, and Abhijit Ghosh (Intrins
 ic); Rick Szeliski (Google Research); and Kartik Venkataraman (Intrinsic)\
 n---------------------\nDecoupling Contact for Fine-Grained Motion Style T
 ransfer\n\nMotion style transfer changes the style of a motion while retai
 ning its content and is useful in computer animations and games. Contact i
 s an essential component of motion style transfer that should be controlle
 d explicitly in order to express the style vividly while enhancing motion 
 naturalness and...\n\n\nXiangjun Tang and Linjun Wu (State Key Laboratory 
 of CAD&CG, Zhejiang University); He Wang (University College London (UCL))
 ; Yiqian Wu (State Key Laboratory of CAD&CG, Zhejiang University); Bo Hu, 
 Songnan Li, Xu Gong, Yuchen Liao, and Qilong Kou (Tencent Technology (Shen
 zhen) Co., Ltd.); and Xiaogang Jin (State Key Laboratory of CAD&CG, Zhejia
 ng University)\n\nRegistration Category: Full Access, Full Access Supporte
 r\n\nLanguage Format: English Language\n\nSession Chair: Hao (Richard) Zha
 ng (Simon Fraser University, Amazon)
END:VEVENT
END:VCALENDAR