AI RESEARCH

GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction

arXiv CS.CV

ArXi:2601.20331v2 Announce Type: replace 3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer visibility and enforce multi-view consistency, leading to a fundamental circular dependency: visibility estimation requires accurate depth, while depth supervision itself is conditioned on visibility. In this work, we revisit multi-view geometric supervision from the perspective of visibility modeling.