AI RESEARCH

GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis

arXiv CS.CV

ArXi:2603.14965v1 Announce Type: new Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer from geometric distortions and limited camera controllability. To overcome these challenges, we