Video-Driven Graph Network-Based Simulators
Saved in:
| Title: | Video-Driven Graph Network-Based Simulators |
|---|---|
| Authors: | Szewczyk, Franciszek, Louppe, Gilles, Sabatelli, Matthia |
| Source: | Machine Learning and the Physical Sciences Workshop (NeurIPS 2024), Vancouver, Canada [CA], 2024-12-15 |
| Publication Year: | 2024 |
| Subject Terms: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning, Engineering, computing & technology, Computer science, Ingénierie, informatique & technologie, Sciences informatiques |
| Description: | Lifelike visualizations in design, cinematography, and gaming rely on precise physics simulations, typically requiring extensive computational resources and detailed physical input. This paper presents a method that can infer a system's physical properties from a short video, eliminating the need for explicit parameter input, provided it is close to the training condition. The learned representation is then used within a Graph Network-based Simulator to emulate the trajectories of physical systems. We demonstrate that the video-derived encodings effectively capture the physical properties of the system and showcase a linear dependence between some of the encodings and the system's motion. |
| Document Type: | conference poster not in proceedings http://purl.org/coar/resource_type/c_18co conferencePoster peer reviewed |
| Language: | English |
| Access URL: | https://orbi.uliege.be/handle/2268/340498 |
| Rights: | open access http://purl.org/coar/access_right/c_abf2 info:eu-repo/semantics/openAccess |
| Accession Number: | edsorb.340498 |
| Database: | ORBi |
| Abstract: | Lifelike visualizations in design, cinematography, and gaming rely on precise physics simulations, typically requiring extensive computational resources and detailed physical input. This paper presents a method that can infer a system's physical properties from a short video, eliminating the need for explicit parameter input, provided it is close to the training condition. The learned representation is then used within a Graph Network-based Simulator to emulate the trajectories of physical systems. We demonstrate that the video-derived encodings effectively capture the physical properties of the system and showcase a linear dependence between some of the encodings and the system's motion. |
|---|