BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T150800
DTEND;TZID=Asia/Tokyo:20241205T151900
UID:siggraphasia_SIGGRAPH Asia 2024_sess135_papers_590@linklings.com
SUMMARY:SKEL-Betweener: a Neural Motion Rig for Interactive Motion Authori
 ng
DESCRIPTION:Technical Papers\n\nDhruv Agrawal (ETH Zürich, DisneyResearch|
 Studios) and Jakob Buhmann, Dominik Borer, Robert W. Sumner, and Martin Gu
 ay (DisneyResearch|Studios)\n\nAuthoring 3D motions is a laborious process
  that requires manipulating and coordinating many control handles over tim
 e. Neural motion representations learned from large motion datasets have r
 ecently shown impressive capabilities in many motion completion tasks. How
 ever, current methods are not designed for interactive motion authoring wo
 rkflows. The reasons being their requirement of a dense context of full po
 ses, which takes considerable time to author, as well as their lack of joi
 nt-level controls for refinement. In this paper, we introduce a Neural Mot
 ion Rig called SKEL-Betweener, tailored to interactive motion authoring. S
 KEL-Betweener is able to generate long motion sequences from two poses onl
 y, and enables intermediate motion authoring via neural motion curves—intu
 itive joint-level controls for positions and orientations. Through user ev
 aluations, we demonstrate the effectiveness of our Neural Motion Rig for e
 fficiently creating and editing motions.\n\nRegistration Category: Full Ac
 cess, Full Access Supporter\n\nLanguage Format: English Language\n\nSessio
 n Chair: Changjian Li (University of Edinburgh)
URL:https://asia.siggraph.org/2024/program/?id=papers_590&sess=sess135
END:VEVENT
END:VCALENDAR