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:20231213T123000
DTEND;TZID=Australia/Melbourne:20231213T124500
UID:siggraphasia_SIGGRAPH Asia 2023_sess163_papers_274@linklings.com
SUMMARY:Object Motion Guided Human Motion Synthesis
DESCRIPTION:Technical Papers\n\nJiaman Li, Jiajun Wu, and Karen Liu (Stanf
 ord University)\n\nModeling human behaviors in contextual environments has
  a wide range of applications in character animation, embodied AI, VR/AR, 
 and robotics. In real-world scenarios, humans frequently interact with the
  environment and manipulate various objects to complete daily tasks. In th
 is work, we study the problem of full-body human motion synthesis for the 
 manipulation of large-sized objects. We propose Object MOtion guided human
  MOtion synthesis (OMOMO), a conditional diffusion framework that can gene
 rate full-body manipulation behaviors from only the object motion. Since n
 aively applying diffusion models fails to precisely enforce contact constr
 aints between the hands and the object, OMOMO learns two separate denoisin
 g processes to first predict hand positions from object motion and subsequ
 ently synthesize full-body poses based on the predicted hand positions. By
  employing the hand positions as an intermediate representation between th
 e two denoising processes, we can explicitly enforce contact constraints, 
 resulting in more physically plausible manipulation motions. With the lear
 ned model, we develop a novel system that captures full-body human manipul
 ation motions by simply attaching a smartphone to the object being manipul
 ated. Through extensive experiments, we demonstrate the effectiveness of o
 ur proposed pipeline and its ability to generalize to unseen objects. Addi
 tionally, as high-quality human-object interaction datasets are scarce, we
  collect a large-scale dataset consisting of 3D object geometry, object mo
 tion, and human motion. Our dataset contains human-object interaction moti
 on for 15 objects, with a total duration of approximately 10 hours.\n\nReg
 istration Category: Full Access\n\nSession Chair: Chek Tien Tan (Singapore
  Institute of Technology)
URL:https://asia.siggraph.org/2023/full-program?id=papers_274&sess=sess163
END:VEVENT
END:VCALENDAR