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:20240214T070246Z
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:Technical Papers, TOG\n\nDhruv Agrawal (ETH Zürich, DisneyRese
 arch|Studios); Martin Guay, Jakob Buhmann, and Dominik Borer (DisneyResear
 ch|Studios); and Robert W. Sumner (DisneyResearch|Studios, ETH Zürich)\n\n
 Posing a 3D character for film or game is an iterative and laborious proce
 ss where many control handles (e.g. joints) need to be manipulated to achi
 eve a compelling result.  Neural Inverse Kinematics (IK) is a new type of 
 IK that enables sparse control over a 3D character pose, and leverages ful
 l body correlations to complete the un-manipulated joints of the body.  Wh
 ile neural IK is promising, current methods are not designed to preserve p
 revious edits in posing workflows. Current models generate a full pose fro
 m the handles only---regardless of what was there previously---making it d
 ifficult to preserve any variations and hindering tasks such as pose and m
 otion editing.\n\nIn this paper, we introduce SKEL-IK, a novel architectur
 e and training scheme that is conditioned on a base pose, and designed to 
 flow information directly onto the skeletal graph structure, such that har
 d constraints can be enforced by blocking information flows at certain joi
 nts. As a result, we are able to satisfy both hard and soft constraints, a
 s well as preserve un-manipulated parts of the body when desired. Finally,
  by controlling the base pose in different ways, we demonstrate the abilit
 y 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
URL:https://asia.siggraph.org/2023/full-program?id=papers_712&sess=sess165
END:VEVENT
END:VCALENDAR