融合多视角立体与高斯溅射，提升弱观测区域的三维重建精度。
CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction
- 用多视图立体点初始化高斯，增强几何先验并减少优化歧义。
- 双向监督机制提升弱约束区域的深度与法向精度，改善几何一致性。
- 采用德劳内图割法提取网格，降低对体素分辨率依赖，适合室外场景。
3D高斯溅射虽能高效生成新视角图像，但在弱观测和遮挡区域难以实现精确网格重建，此时高斯原语可能演化为不稳定或几何不一致的结构。本文提出CoMVS-GS框架，将多视图立体（Multi-View Stereo）与高斯溅射相结合。该方法基于密集多视图立体点初始化高斯原语，采用预扁平化尺度与法向对齐方向，相比稀疏运动恢复结构初始化具有更强几何先验，有效降低早期优化的歧义性。进一步引入PatchMatch-3DGS互监督机制：高斯渲染的深度与法向用于初始化PatchMatch优化，而优化后的深度则反向监督高斯优化，从而提升弱约束区域的几何质量。表面提取阶段，以德劳内图割网格化流程替代截断有符号距离场体素融合，降低对体素分辨率的敏感性，同时保留可见性一致的表面证据。在DTU、GauU-Scene V2和MatrixCity数据集上的实验表明，CoMVS-GS在物体级重建上保持竞争力，并显著提升户外场景的几何精度与网格紧凑性，同时维持高质量渲染效果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。