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:20260114T163643Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T094000
DTEND;TZID=Australia/Melbourne:20231214T095000
UID:siggraphasia_SIGGRAPH Asia 2023_sess165_papers_712@linklings.com
SUMMARY:Pose and Skeleton-aware Neural IK for Pose and Motion Editing
DESCRIPTION:Dhruv Agrawal (ETH Zürich, DisneyResearch|Studios); Martin Gua
 y, Jakob Buhmann, and Dominik Borer (DisneyResearch|Studios); and Robert W
 . Sumner (DisneyResearch|Studios, ETH Zürich)\n\nPosing a 3D character for
  film or game is an iterative and laborious process where many control han
 dles (e.g. joints) need to be manipulated to achieve a compelling result. 
  Neural Inverse Kinematics (IK) is a new type of IK that enables sparse co
 ntrol over a 3D character pose, and leverages full body correlations to co
 mplete the un-manipulated joints of the body.  While neural IK is promisin
 g, current methods are not designed to preserve previous edits in posing w
 orkflows. Current models generate a full pose from the handles only---rega
 rdless of what was there previously---making it difficult to preserve any 
 variations and hindering tasks such as pose and motion editing.\n\nIn this
  paper, we introduce SKEL-IK, a novel architecture and training scheme tha
 t is conditioned on a base pose, and designed to flow information directly
  onto the skeletal graph structure, such that hard constraints can be enfo
 rced by blocking information flows at certain joints. As a result, we are 
 able to satisfy both hard and soft constraints, as well as preserve un-man
 ipulated parts of the body when desired. Finally, by controlling the base 
 pose in different ways, we demonstrate the ability of our model to perform
  tasks such as generating variations and quickly editing poses and motions
 ; with less erosion of the base poses compared to the current state-of-the
 -art.\n\nRegistration Category: Full Access\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_712&sess=sess165
END:VEVENT
END:VCALENDAR