Diffusion Implicit Policy for Unpaired Scene-aware Motion Synthesis

Understand

Scene-aware motion synthesis has been widely researched recently due to its numerous applications.

• Prevailing methods rely heavily on paired motion-scene data, while it is difficult to generalize to diverse scenes when trained only on a few specific ones.
• Thus, we propose a unified framework, termed Diffusion Implicit Policy (DIP), for scene-aware motion synthesis, where paired motion-scene data are no longer necessary.
• In this paper, we disentangle human-scene interaction from motion synthesis during training, and then introduce an interaction-based implicit policy into motion diffusion during inference.