AI RESEARCH

AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting

arXiv CS.CV

ArXi:2603.25129v1 Announce Type: new While 3D Vision Foundation Models (3DVFMs) have nstrated remarkable zero-shot capabilities in visual geometry estimation, their direct application to generalizable novel view synthesis (NVS) remains challenging. In this paper, we propose AirSplat, a novel