Human Motion and Interaction Synthesis

A key step towards understanding human behavior is predicting 3D human motion. Our group has made several contributions in this direction. First, we focused on learning robust and efficient marker-based representations of 3D human bodies in motion. We proposed new generative motion models and optimization algorithms to synthesize realistic human motion sequences. Second, we developed an efficient and fully automated system to generate long-term, even infinite motion for various human shapes. Specifically, given a 3D scene, e.g., digital architecture, our model can generate a massive number of virtual humans, who possess diverse body shapes, move perpetually, and have plausible body-scene contact in an automatic,efficient, scalable, and controllable manner. Besides top-tier scientific publications, our motion synthesis method is the key component for the exhibition of inhabiting a virtual city hosted by theGuggenheim Museum Bilbao.