Presentation

<
Flexible Motion In-betweening With Diffusion Models
SessionCharacter Animation From Data
DescriptionWe introduce CondMDI, a simple and unified diffusion-based approach for text and keyframe guided motion in-betweening. CondMDI accommodates flexible keyframe placements and partial keyframes, generating high-quality and diverse motions coherent with the input constraints. Evaluation on the HumanML3D dataset showcases CondMDI's effectiveness on a diverse set of motion in-betweening tasks.
Authors
Setareh Cohan
University of British Columbia
Guy Tevet
Tel Aviv University
Daniele Reda
University of British Columbia
Xue Bin Peng
Simon Fraser University
NVIDIA Research
Michiel van de Panne
University of British Columbia
Event Type
Technical Paper
TimeWednesday, 31 July 202411:15am - 11:25am MDT
LocationMile High 4
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Wednesday, 31 July 202410:45am - 12:15pm MDTMile High 4
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Wednesday
Next PresentationNext PresentationWalkTheDog: Cross-morphology Motion Alignment via Phase Manifolds