My name is Shi Boao. My English name is Bowie. I am currently a research assistant at Penn GRASP Lab. I am also a final year undergraduate majoring in Computer Science from The University of Hong Kong.
My research interests lie in general 3D and 4D. Several directions/topics I am interested in:
- Character animation
- Feedforward 3D/4D reconstruction
- Video world model
- Application in robotics
I am quite interested in the following questions:
- How can we learn dynamics and interaction of the real world from streaming monocular observation (captured by any devices)?
- How can we encode motion, deformation, and interaction such that they obey physical law and generalize?
- How can we extract scalable and generalizable priors of world dynamics and interaction causality between human and object, object and object, and how to exploit it as a foundation for downstream robotics tasks?