2 papers
cs.CV2025
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…
cs.CV2025
TesserAct: Learning 4D Embodied World Models
Haoyu Zhen, Qiao Sun, Hongxin Zhang +4
This paper presents an effective approach for learning novel 4D embodied world models, which predict the dynamic evolution of 3D scenes over time in response to an embodied agent's…