Presentation
DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds
SessionTechnical Papers
Event Type
Technical Paper
Research & Education
Virtual
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Time
Location
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.
