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:20240214T070244Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231213T124500
DTEND;TZID=Australia/Melbourne:20231213T125500
UID:siggraphasia_SIGGRAPH Asia 2023_sess163_papers_440@linklings.com
SUMMARY:DROP: Dynamics Responses from Human Motion Prior and Projective Dy
 namics
DESCRIPTION:Technical Papers\n\nYifeng Jiang (Stanford University), Jungda
 m Won (Seoul National University), Yuting Ye (Meta Reality Labs Research),
  and C. Karen Liu (Stanford University)\n\nSynthesizing realistic human mo
 vements, dynamically responsive to the environment, is a long-standing obj
 ective in character animation, with applications in computer vision, sport
 s, and healthcare, for motion prediction and data augmentation. Recent kin
 ematics-based generative motion models offer impressive scalability in mod
 eling extensive motion data, albeit without an interface to reason about a
 nd interact with physics. While simulator-in-the-loop learning approaches 
 enable highly physically realistic behaviors, the challenges in training o
 ften affect scalability and adoption. We introduce DROP, a novel framework
  for modeling Dynamics Responses of humans using generative mOtion prior a
 nd Projective dynamics. DROP can be viewed as a highly stable, minimalist 
 physics-based human simulator that interfaces with a kinematics-based gene
 rative motion prior. Utilizing projective dynamics, DROP allows flexible a
 nd simple integration of the learned motion prior as one of the projective
  energies, seamlessly incorporating control provided by the motion prior w
 ith Newtonian dynamics. Serving as a model-agnostic plug-in, DROP enables 
 us to fully leverage recent advances in generative motion models for physi
 cs-based motion synthesis. We conduct extensive evaluations of our model a
 cross different motion tasks and various physical perturbations, demonstra
 ting the scalability and diversity of responses.\n\nRegistration Category:
  Full Access\n\nSession Chair: Chek Tien Tan (Singapore Institute of Techn
 ology)
URL:https://asia.siggraph.org/2023/full-program?id=papers_440&sess=sess163
END:VEVENT
END:VCALENDAR