Visual Physics: Discovering Physical Laws from Videos

TL;DR

This paper presents a method for machines to learn physical laws directly from videos of elementary phenomena, without prior physics knowledge, by analyzing bounding box streams to identify governing equations and parameters.

Contribution

It introduces a novel approach to discover physical laws from videos with no prior physics knowledge, validated on elementary phenomena with known equations.

Findings

Successfully discovered laws of projectile and circular motion

Achieved accurate identification of governing parameters

Validated approach with ground truth verification

Abstract

In this paper, we teach a machine to discover the laws of physics from video streams. We assume no prior knowledge of physics, beyond a temporal stream of bounding boxes. The problem is very difficult because a machine must learn not only a governing equation (e.g. projectile motion) but also the existence of governing parameters (e.g. velocities). We evaluate our ability to discover physical laws on videos of elementary physical phenomena, such as projectile motion or circular motion. These elementary tasks have textbook governing equations and enable ground truth verification of our approach.