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:20260114T163633Z
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:Tianyu Li (Georgia Institute of Technology), Jungdam Won (Seou
 l National University), Alexander Clegg (Meta), Jeonghwan Kim (Georgia Ins
 titute of Technology), Akshara Rai (Meta), and Sehoon Ha (Georgia Institut
 e of Technology)\n\nMotion retargeting is a promising approach for generat
 ing natural and compelling motions for nonhuman characters. However, it is
  challenging to translate human movements into semantically equivalent mot
 ions for target characters with very different morphologies due to ambigui
 ty. This work presents a novel learning-based motion retargeting framework
 , Adversarial Correspondence Embedding (ACE), to retarget human motions on
 to target characters with different body dimensions and structures. Our fr
 amework is designed to produce natural and feasible robot motions by lever
 aging generative-adversarial networks (GANs) while preserving high-level m
 otion semantics by introducing an additional feature loss. In addition, we
  pretrain a robot motion prior that can be controlled in a latent embeddin
 g space and seek to establish a compact correspondence. We demonstrate tha
 t the proposed framework can produce convincing retargeted motions for thr
 ee different characters, a quadrupedal robot with a manipulator, a crab ch
 aracter, and a wheeled manipulator. We further validate the design choices
  of our framework by conducting baseline comparisons and user studies. We 
 also demonstrate the sim-to-real of the retargeted motions by transferring
  it to the real Spot robot.\n\nRegistration Category: Full Access, Enhance
 d Access, Trade Exhibitor, Experience Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_1057&sess=sess20
 9
END:VEVENT
END:VCALENDAR