VeloGauss: Learning Physically Consistent Gaussian Velocity Fields from Videos

ArXi:2605.10567v1 Announce Type: new In this paper, we aim to jointly model the geometry, appearance, and physical information of 3D scenes solely from dynamic multi-view videos, without relying on any physical priors. Existing works typically employ physical losses merely as soft constraints or integrate physical simulations into neural networks; however, these approaches often fail to effectively learn complex motion physics.