Problem
Research questions and friction points this paper is trying to address.
3D Gaussian Splatting
surface reconstruction
weakly observed regions
occluded regions
geometric consistency
CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction
🤖 AI Summary
针对弱观测和遮挡区域的准确网格重建难题，提出结合多视图立体与3D高斯点云的CoMVS-GS框架，通过几何先验增强及相互监督优化方法提升重建质量。
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
CoMVS-GS
Gaussian Splatting
Multi-View Stereo
PatchMatch-3DGS Mutual Supervision
Delaunay graph-cut meshing
🔎 Similar Papers
No similar papers found.
