TY  - JOUR
TI  - DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds
AU  - Starke, S.
AU  - Mason, I.
AU  - Komura, T.
PY  - 2022
DA  - 2022/07//
JO  - ACM Transactions on Graphics (SIGGRAPH 2022)
AB  - Starke, Mason, and Komura (2022) introduce a periodic autoencoder that discovers the phase structure of motion data automatically, learning a continuous manifold that supports smooth transitions between locomotion states without requiring manually annotated phase signals. The method received the SIGGRAPH 2022 Best Paper award and is animation-native, having been designed and evaluated entirely within the character animation domain. It is the current reference for neural phase-based character control and has demonstrably shaped the direction of interactive character locomotion research.
KW  - character-animation
KW  - motion-synthesis
KW  - generative-ai
UR  - https://dl.acm.org/doi/10.1145/3528223.3530178
LA  - en
ER  -