Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces

ICLR 2019

Published May 6, 2019

Senthil Purushwalkam, Abhinav Gupta, Danny Kaufman, Bryan Russell

We introduce an approach to model surface properties governing bounces in everyday scenes. Our model learns end-to-end, starting from sensor inputs, to predict post-bounce trajectories and infer two underlying physical properties that govern bouncing - restitution and effective collision normals. Our model, Bounce and Learn, comprises two modules – a Physics Inference Module (PIM) and a Visual Inference Module (VIM). VIM learns to infer physical parameters for locations in a scene given a single still image, while PIM learns to model physical interactions for the prediction task given physical parameters and observed pre-collision 3D trajectories. To demonstrate our results, we introduce the Bounce Dataset comprising 5K RGB-D videos of bouncing trajectories of a foam ball to probe surfaces of varying shapes and materials in everyday scenes including homes and offices.

Learn More