Presentation

<
Multi-Person Interaction Generation from Two-Person Motion Priors
SessionRigging & Interaction
DescriptionGenerate exciting multi-character interactions, such as team fights, with our training-free method! Multi-character interactions can be decomposed into multiple two-person interactions using a directed graph, which enables repurposing large pre-trained two-character motion synthesis models without any multi-character data. You can compose and vary multi-character interactions spatially and temporally!
Authors
Wenning Xu
University of Glasgow
Shiyu Fan
University of Glasgow
Paul Henderson
University of Glasgow
Edmond S. L. Ho
University of Glasgow
Event Type
Technical Paper
TimeWednesday, 13 August 20252:30pm - 2:40pm PDT
LocationWest Building, Rooms 220-222
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 20252:00pm - 3:30pm PDTWest Building, Rooms 220-222
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationLarge-Scale Multi-Character Interaction Synthesis
Similar Presentations
Large-Scale Multi-Character Interaction Synthesis
PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers
PLT: Part-Wise Latent Tokens as Adaptable Motion Priors for Physically Simulated Characters