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_440@linklings.com
SUMMARY:DROP: Dynamics Responses from Human Motion Prior and Projective Dy
 namics
DESCRIPTION:Yifeng Jiang (Stanford University), Jungdam Won (Seoul Nationa
 l University), Yuting Ye (Meta Reality Labs Research), and C. Karen Liu (S
 tanford University)\n\nSynthesizing realistic human movements, dynamically
  responsive to the environment, is a long-standing objective in character 
 animation, with applications in computer vision, sports, and healthcare, f
 or motion prediction and data augmentation. Recent kinematics-based genera
 tive motion models offer impressive scalability in modeling extensive moti
 on data, albeit without an interface to reason about and interact with phy
 sics. While simulator-in-the-loop learning approaches enable highly physic
 ally realistic behaviors, the challenges in training often affect scalabil
 ity and adoption. We introduce DROP, a novel framework for modeling Dynami
 cs Responses of humans using generative mOtion prior and Projective dynami
 cs. DROP can be viewed as a highly stable, minimalist physics-based human 
 simulator that interfaces with a kinematics-based generative motion prior.
  Utilizing projective dynamics, DROP allows flexible and simple integratio
 n of the learned motion prior as one of the projective energies, seamlessl
 y incorporating control provided by the motion prior with Newtonian dynami
 cs. Serving as a model-agnostic plug-in, DROP enables us to fully leverage
  recent advances in generative motion models for physics-based motion synt
 hesis. We conduct extensive evaluations of our model across different moti
 on tasks and various physical perturbations, demonstrating the scalability
  and diversity of responses.\n\nRegistration Category: Full Access, Enhanc
 ed Access, Trade Exhibitor, Experience Hall Exhibitor\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_440&sess=sess209
END:VEVENT
END:VCALENDAR