Visual Physics: Discovering Physical Laws from Videos
arXiv:1911.11893
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.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Interaction Networks for Learning about Objects, Relations and Physics
- Discovering physical concepts with neural networks
- Neural Lander: Stable Drone Landing Control using Learned Dynamics
- Unrolled Optimization with Deep Priors
- GP-RVM: Genetic Programing-based Symbolic Regression Using Relevance Vector Machine
- Neural-Guided Symbolic Regression with Asymptotic Constraints
- Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces
- Perceiving Physical Equation by Observing Visual Scenarios
- Deep Shape from Polarization