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:20240214T070240Z
LOCATION:Darling Harbour Theatre\, Level 2 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T093000
DTEND;TZID=Australia/Melbourne:20231212T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess209_papers_1057@linklings.com
SUMMARY:ACE: Adversarial Correspondence Embedding for Cross Morphology Mot
 ion Retargeting from Human to Nonhuman Characters
DESCRIPTION:Technical Papers\n\nTianyu Li (Georgia Institute of Technology
 ), Jungdam Won (Seoul National University), Alexander Clegg (Meta), Jeongh
 wan Kim (Georgia Institute of Technology), Akshara Rai (Meta), and Sehoon 
 Ha (Georgia Institute of Technology)\n\nMotion retargeting is a promising 
 approach for generating natural and compelling motions for nonhuman charac
 ters. However, it is challenging to translate human movements into semanti
 cally equivalent motions for target characters with very different morphol
 ogies due to ambiguity. This work presents a novel learning-based motion r
 etargeting framework, Adversarial Correspondence Embedding (ACE), to retar
 get human motions onto target characters with different body dimensions an
 d structures. Our framework is designed to produce natural and feasible ro
 bot motions by leveraging generative-adversarial networks (GANs) while pre
 serving high-level motion semantics by introducing an additional feature l
 oss. In addition, we pretrain a robot motion prior that can be controlled 
 in a latent embedding space and seek to establish a compact correspondence
 . We demonstrate that the proposed framework can produce convincing retarg
 eted motions for three different characters, a quadrupedal robot with a ma
 nipulator, a crab character, and a wheeled manipulator. We further validat
 e the design choices of our framework by conducting baseline comparisons a
 nd user studies. We also demonstrate the sim-to-real of the retargeted mot
 ions by transferring it to the real Spot robot.\n\nRegistration Category: 
 Full Access, Enhanced Access, Trade Exhibitor, Experience Hall Exhibitor
URL:https://asia.siggraph.org/2023/full-program?id=papers_1057&sess=sess20
 9
END:VEVENT
END:VCALENDAR