Presentation / Installation


Bodyformer: Semantics-guided 3D Body Gesture Synthesis With Transformer
SessionCharacter Animation: Knowing What To Do With Your Hands
DescriptionThis paper presents a new variational transformer framework for synthesizing 3D body gestures driven by speech. The system uses a mode position embedding and intra-modal pre-training to learn motion patterns from limited conversational data. Extensive studies show that the system can generate realistic and diverse gestures similar to the ground-truth.
Authors
Kunkun Pang
Guangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences
Dafei Qin
University of Hong Kong
Yingruo Fan
University of Hong Kong
Julian Habekost
University of Edinburgh
Takaaki Shiratori
Facebook Reality Labs
Junichi Yamagishi
National Institute of Informatics
Taku Komura
University of Hong Kong
Event Type
Technical Paper
TimeMonday, 7 August 20232:11pm - 2:22pm PDT
LocationPetree Hall C
ACM Digital Library Technical Papers pdfs
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Monday, 7 August 20232pm - 3:30pm PDTPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation/Simulation
Artificial Intelligence/Machine Learning
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models