Zhiyang (Frank) Dou (@frankzydou)
2025-06-20 | โค๏ธ 138 | ๐ 27
Check out ๐Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry & Physics for Mesh-Free Simulation CVPR2025, from @LingjieLiu1โs lab at UPenn. Congrats to @MorPhLingXD! Vid2Sim aims to achieve system identification by reconstructing geometry, appearance, and physical properties directly from video. It combines learned data priors with closed-loop optimization: a feed-forward predictor trained on physical prior, followed by fast refinement via Neural Jacobian and mesh-free simulation. The system delivers simulation-ready outputs in minutes, with strong generalization across objects and materials. ๐ Project page: https://czzzzh.github.io/Vid2Sim/
PhysicalAI AIGC CV CG simulation graphics
๐ Related
See similar notes in domain-vision-3d, domain-simulation