Presentation

DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds
SessionRoundtable Session: Character Animation
Authors
Sebastian Starke
Ian Mason
Taku Komura
Event Type
Technical Paper
Keywords
Animation/Simulation
Interest Areas
Research & Education
Presentation Types
In Person
Registration Categories
Full Conference Supporter
Full Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Recordings
This session WILL NOT be recorded.
TimeThursday, 11 August 20229am - 9:08am PDT
LocationEast Building, Ballroom A/B
DescriptionWe present the Periodic Autoencoder that can learn the spatial-temporal structure of body movements from unstructured motion data. The network produces a multi-dimensional phase manifold that helps enhance neural character controllers and motion matching for a variety of tasks, including diverse locomotion, style-based movements, dancing to music, or football dribbling.
Authors
Sebastian Starke
University of Edinburgh
Electronic Arts
Ian Mason
University of Edinburgh
Taku Komura
University of Hong Kong