BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163644Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T162500
DTEND;TZID=Australia/Melbourne:20231214T171600
UID:siggraphasia_SIGGRAPH Asia 2023_sess166@linklings.com
SUMMARY:Flesh & Bones
DESCRIPTION:Learning Multivariate Empirical Mode Decomposition for Spectra
 l Motion Editing\n\nThis research proposes an architecture for neural netw
 orks to learn multivariate empirical mode decomposition. Editing the decom
 posed non-linear frequency components achieves novel tasks for character a
 nimation synthesis.\n\n\nRan Dong (Chukyo University), Soichiro Ikuno (Tok
 yo University of Technology), and Xi Yang (Jilin University)\n------------
 ---------\nRobust Skin Weights Transfer via Weight Inpainting\n\nA novel r
 obust method for automated transferring of skin weights between meshes wit
 h significantly different shapes that surpasses existing commercial softwa
 re and research methods.\n\n\nRinat Abdrashitov, Kim Raichstat, Jared Mons
 en, and David Hill (Epic Games)\n---------------------\nSFLSH: Shape-Depen
 dent Soft-Flesh Avatars\n\nWe present a multi-person soft-tissue avatar mo
 del. This model maps a body shape descriptor to heterogeneous geometric an
 d mechanical parameters of a soft-tissue model across the body, effectivel
 y producing a shape-dependent parametric soft avatar model. The design of 
 the model overcomes two major c...\n\n\nPablo Ramón, Cristian Romero, Javi
 er Tapia, and Miguel A. Otaduy (Universidad Rey Juan Carlos)\n------------
 ---------\nFrom Skin to Skeleton : Towards Biomechanically Accurate 3D Dig
 ital Humans\n\nGreat progress has been made in estimating 3D human pose an
 d shape from images and video by training neural networks to directly regr
 ess the parameters of parametric human models like SMPL.\nHowever, existin
 g body models have simplified kinematic structures that do not correspond 
 to accurate joint lo...\n\n\nMarilyn Keller (Max Planck Institute for Inte
 lligent Systems), Keenon Werling (Stanford University), Soyong Shin (Max-P
 lanck-Institut für Informatik), Scott Delp (Stanford), Sergi Pujades (INRI
 A), Karen Liu (Stanford University), and Michael Black (Max Planck Institu
 te for Intelligent Systems)\n---------------------\nNeural Motion Graph\n\
 nDeep learning techniques have been employed to design a controllable huma
 n motion synthesizer. Despite their potential, however, designing a neural
  network-based motion synthesis that enables flexible user interaction, fi
 ne-grained controllability, and the support of new types of motions at red
 uced ...\n\n\nHongyu Tao, Shuaiying Hou, Changqing Zou, Hujun Bao, and Wei
 wei Xu (Zhejiang University)\n\nRegistration Category: Full Access\n\nSess
 ion Chair: Seungbae Bang (Amazon)
END:VEVENT
END:VCALENDAR