AI RESEARCH
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
arXiv CS.CV
•
ArXi:2603.08254v1 Announce Type: new Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have nstrated strong performance in static reconstruction but still struggle to capture dynamic motion. To address these limitations, we propose DynamicVGGT, a unified feed-forward framework that extends VGGT from static 3D perception to dynamic 4D reconstruction.