Presentation

<
Text-guided Synthesis of Crowd Animation
SessionCharacter Animation: 2D, 3D, Robot
DescriptionThis paper presents a novel approach to automatically generate crowd behaviors from high-level text descriptions. The group-wise, velocity-field-based representation of collective agent behaviors is used and seamlessly integrated with diffusion models and large language models. This work paves the way toward automatic crowd behavior generation for virtual environments.
Authors
Xuebo Ji
University of Hong Kong
Centre for Transformative Garment Production (TransGP)
Zherong Pan
Tencent America
Xifeng Gao
Tencent America
Jia Pan
University of Hong Kong
Centre for Transformative Garment Production (TransGP)
Event Type
Technical Paper
TimeThursday, 1 August 202410:55am - 11:05am 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
Thursday, 1 August 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
Thursday
Next PresentationNext PresentationInteractive Design of Stylized Walking Gaits for Robotic Characters