Perceiving Physical Equation by Observing Visual Scenarios
This addresses the challenge of enabling machines to learn universal physical laws from visual data, which is a step toward general AI, though it is incremental as it builds on existing methods for visual inference.
The paper tackles the problem of inferring invariant physical equations from visual scenarios, such as deriving gravitational acceleration from watching a free-falling object, and presents a pipeline that successfully discovers physical equations in synthetic videos with different visual appearances.
Inferring universal laws of the environment is an important ability of human intelligence as well as a symbol of general AI. In this paper, we take a step toward this goal such that we introduce a new challenging problem of inferring invariant physical equation from visual scenarios. For instance, teaching a machine to automatically derive the gravitational acceleration formula by watching a free-falling object. To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world. Generally, the Observer Engine watches the visual scenarios and then extracting the physical properties of objects. The Physicist Engine analyses these data and then summarizing the inherent laws of object dynamics. Specifically, the learned laws are expressed by mathematical equations such that they are more interpretable than the results given by common probabilistic models. Experiments on synthetic videos have shown that our pipeline is able to discover physical equations on various physical worlds with different visual appearances.