CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction

arXiv:2608.18413v1 Announce Type: new Abstract: 3D Gaussian Splatting enables efficient novel view synthesis, but accurate mesh reconstruction remains difficult in weakly observed and occluded regions, where Gaussian primitives may grow into unstable or geometrically inconsistent structures. We propose CoMVS-GS, a general surface reconstruction framework that combines Multi-View Stereo with Gaussian splatting. CoMVS-GS initializes Gaussian primitives from dense multi-view stereo points with pre-flattened scales and normal-aligned orientations, providing stronger geometric priors than sparse structure-from-motion initialization and reducing ambiguity during early optimization. It further introduces PatchMatch-3DGS Mutual Supervision, where Gaussian-rendered depths and normals initialize PatchMatch refinement, and refined PatchMatch depths supervise Gaussian optimization to improve weakly constrained geometry. For surface extraction, CoMVS-GS replaces truncated signed distance field voxel fusion with a Delaunay graph-cut meshing pipeline, reducing sensitivity to voxel resolution while preserving visibility-consistent surface evidence. Experiments on DTU, GauU-Scene V2, and MatrixCity show that CoMVS-GS remains competitive on object-level reconstruction and improves geometric accuracy and mesh compactness in outdoor scenes while maintaining high rendering quality.

Related

• SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
• GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
• Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction
• High-Fidelity Surface Splatting-Based 3D Reconstruction from Multi-View Images

Source: arXiv cs.CV | 2026-08-20