AI RESEARCH
Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors
arXiv CS.CV
•
ArXi:2604.09366v1 Announce Type: new Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address this, we present a framework designed to disentangle dynamic and static components by modeling uncertainty across different stages of the reconstruction process. Our approach