Visual Physics: Discovering Physical Laws from Videos
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Nov 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 5; 2026: 2.
10 papers.
- 2025NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamicscited by 41
- 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamicscited by 32
- 2025Generative Physical AI in Vision: A Surveycited by 24
- 2022Neural Implicit Representations for Physical Parameter Inference from a Single Videocited by 19
- 2025Synthetic Video Enhances Physical Fidelity in Video Synthesiscited by 15
- 2025MASIV: Toward Material-Agnostic System Identification from Videoscited by 9
- 2023Synthetic Data in Healthcarecited by 8
- 2026Deltaynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videoscited by 3
- 2025Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videoscited by 1
- 2026PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generationcited by 0
- 2026PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation11 Oct 2026
- 2026Deltaynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos20 May 2026
- 2025Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videos30 Sep 2025
- 2025NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics25 Sep 2025
- 2025MASIV: Toward Material-Agnostic System Identification from Videos1 Aug 2025
- 2025Synthetic Video Enhances Physical Fidelity in Video Synthesis26 Mar 2025
- 2025Generative Physical AI in Vision: A Survey19 Jan 2025
- 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics10 Oct 2024
- 2023Synthetic Data in Healthcare6 Apr 2023
- 2022Neural Implicit Representations for Physical Parameter Inference from a Single Video29 Apr 2022