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

• URL: http://arxiv.org/abs/2608.18413v1
• Date: Wed, 19 Aug 2026 00:46:19 GMT
• Title: CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction
• Abstract summary: CoMVS-GS is a general surface reconstruction framework that combines Multi-View Stereo with Gaussian splatting.<n>It initializes primitives from dense multi-view stereo points with pre-flattened scales and normal-aligned orientations.<n>For surface extraction, CoMVS-GS replaces truncated signed distance field voxel fusion with a Delaunay graph-cut meshing pipeline.
• Score: 4.2932025928748425
• License: http://creativecommons.org/licenses/by/4.0/
• 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 papers

• 2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction [20.01352292373102]
  2D Gaussian Splatting (2DGS) is proposed to enable view-consistent and geometrically accurate surface reconstruction from multi-view images.<n>We enhance 2DGS by incorporating monocular depth and normal priors to improve both geometric accuracy and robustness.<n>We evaluate our method on the DTU dataset, where it achieves photorealistic state-of-the-art results in mesh reconstruction while preserving high-quality novel view.
  arXiv  Detail & Related papers  (2026-05-01T11:09:29Z)
• GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction [15.170414649311441]
  3D Gaussian Splatting enables efficient optimization and high-quality rendering, yet accurate surface reconstruction remains challenging.<n>We introduce a visibility-aware multi-view geometric consistency constraint that aggregates the visibility of shared Gaussian primitives across views.<n>We also propose a progressive quadtree-calibrated Monocular depth constraint that performs block-wise affine calibration from coarse to fine spatial scales.
  arXiv  Detail & Related papers  (2026-01-28T07:48:51Z)
• SVRecon: Sparse Voxel Rasterization for Surface Reconstruction [60.92372415355283]
  We extend the recently proposed sparse voxelization paradigm to the task of high-fidelity surface reconstruction by integrating SVRecon.<n>Our method achieves strong reconstruction accuracy while having consistently speedy convergence.
  arXiv  Detail & Related papers  (2025-11-21T16:32:01Z)
• VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment [48.147381011235446]
  3D Gaussian Splatting has recently emerged as an efficient solution for real-time novel view synthesis.<n>We propose a novel method that enhances the geometric representation of 3D Gaussians through view alignment.<n>Our method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis.
  arXiv  Detail & Related papers  (2025-10-13T14:44:50Z)
• OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction [10.746979229164815]
  OMeGa is an end-to-end framework that jointly optimize an explicit triangle mesh and 2D Gaussian splats.<n>OMeGa achieves state-of-the-art performance on challenging indoor reconstruction benchmarks.
  arXiv  Detail & Related papers  (2025-09-29T05:43:40Z)
• Gaussian Set Surface Reconstruction through Per-Gaussian Optimization [9.451254271017767]
  3D Gaussian Splatting (3DGS) effectively synthesizes novel views through its flexible representation, yet fails to accurately reconstruct scene geometry.<n>We propose Gaussian Set Surface Reconstruction (GSSR), a method designed to distribute Gaussians evenly along the latent surface while aligning their dominant normals with the surface normal.<n>GSSR enforces fine-grained geometric alignment through a combination of pixel-level and Gaussian-level single-view normal consistency and multi-view photometric consistency.
  arXiv  Detail & Related papers  (2025-07-25T03:31:47Z)
• Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views [45.125032766506536]
  We propose Sparse2DGS, an MVS-d Gaussian Splatting pipeline for complete and accurate reconstruction.<n>Our key insight is to incorporate the geometric-prioritized enhancement schemes, allowing for direct and robust geometric learning under ill-posed conditions.<n>Sparse2DGS outperforms existing methods by notable margins while being $2times$ faster than the NeRF-based fine-tuning approach.
  arXiv  Detail & Related papers  (2025-04-29T02:47:02Z)
• SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction [48.228533595941556]
  We propose a novel method called SolidGS to address this problem.<n>We observed that the reconstructed geometry can be severely inconsistent across multi-views.<n>With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction.
  arXiv  Detail & Related papers  (2024-12-19T21:04:43Z)
• GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction [79.42244344704154]
  GausSurf employs geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene.<n>Our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time.
  arXiv  Detail & Related papers  (2024-11-29T03:54:54Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [86.87464903285208]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields [100.90743697473232]
  Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering.<n>Existing methods often incorporate depth priors from dense estimation networks but overlook the inherent multi-view consistency in input images.<n>We propose a view synthesis framework based on 3D Gaussian Splatting, enabling scene reconstruction from sparse views.
  arXiv  Detail & Related papers  (2024-10-15T08:39:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.