4 papers
PhyMo: Learning Physical Dynamics with Accurate and Continuous Motion from Multi-View Videos
Shangjia Liu, Jinxi Li, Siyuan Zhou +2
Recovering dynamic 3D scene geometry, appearance, and the physical motion states that govern scene evolution from multi-view videos is important yet challenging. A key difficulty i…
PhysInOne: Visual Physics Learning and Reasoning in One Suite
Siyuan Zhou, Hejun Wang, Hu Cheng +36
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to mere…
RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
Shenxing Wei, Jinxi Li, Yafei Yang +2
In this paper, we present a generalizable method for 3D surface reconstruction from raw point clouds or pre-estimated 3D Gaussians by 3DGS from RGB images. Unlike existing coordina…
FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
Jinxi Li, Ziyang Song, Siyuan Zhou +1
In this paper, we aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos. By applying various governing PDEs as PINN losses or incorpo…