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.
Figures & tables
Figure 1: Qualitative comparison between PGSR and CoMVS-GS in rendered images, depth maps, and normal maps. CoMVS-GS produces flatter geometry in weakly constrained regions while preserving fine scene details.
Figure 2: Overview of CoMVS-GS. (a) MVS dense points provide pre-flattened and normal-aligned Gaussian initialization without requiring a precomputed mesh. (b) PatchMatch-3DGS Mutual Supervision refines Gaussian geometry, with MVS-style filtering used for PGSR-style source views. (c) TSDF-free surface extraction through a Delaunay graph-cut meshing pipeline.
Figure 3: Illustration of PatchMatch-3DGS Mutual Supervision.
Method
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
NeRF [ 23 ]
1.90
1.60
1.85
0.58
2.28
1.27
1.47
1.67
2.05
1.07
0.88
2.53
1.06
1.15
0.96
1.49
VolSDF [ 33 ]
1.14
1.26
0.81
0.49
1.25
0.70
0.72
1.29
1.18
0.70
0.66
1.08
0.42
0.61
0.55
0.86
NeuS [ 29 ]
1.00
1.37
0.93
0.43
1.10
0.65
0.57
1.48
1.09
0.83
0.52
1.20
0.35
0.49
0.54
0.84
Neuralangelo [ 20 ]
0.37
0.72
0.35
0.35
0.87
0.54
0.53
1.29
0.97
0.73
0.47
0.74
0.32
0.41
0.43
0.61
3DGS [ 17 ]
2.14
1.53
2.08
1.68
3.49
2.21
1.43
2.07
2.22
1.75
1.79
2.55
1.53
1.52
1.50
1.96
2DGS [ 13 ]
0.48
0.91
0.39
0.39
1.01
0.83
0.81
1.36
1.27
0.76
0.70
1.40
0.40
0.76
0.52
0.80
Table 1: Quantitative comparison on the DTU dataset. We report Chamfer Distance, with the best and second-best results highlighted in bold and underlined.
Method
Visual Metrics
Geometric Metrics
#Faces ( ×106 )
PSNR ↑
SSIM ↑
LPIPS ↓
MAE (m) ↓
RMSE (m) ↓
Neuralangelo [ 20 ]
24.650
0.686
0.404
0.816
1.473
33.063
2DGS [ 13 ]
25.569
0.799
0.277
0.853
1.408
35.954
RaDe-GS [ 35 ]
25.481
0.845
0.198
0.680
1.330
39.065
PGSR [ 4 ]
28.370
0.886
0.174
0.670
1.284
50.169
CityGS-X [ 10 ]
27.783
0.883
0.150
0.755
1.466
146.591
Table 2: Quantitative comparison on the Sub-Village, Sub-Technology College, and Sub-Small City. We report visual metrics, geometric metrics, and the average number of mesh faces. Dashes indicate unavailable or inapplicable metrics.
Figure 4: Qualitative comparison on DTU scan 40 and Sub-Technology College. From left to right, each row shows the input image, PGSR, OpenMVS, and CoMVS-GS.
Figure 5: Ablation on the Sub-Small City, showing the effects of PatchMatch supervision, Delaunay graph-cut meshing, and dense point cloud initialization.
Variant
Visual Metrics
Geometric Metrics
PSNR ↑
SSIM ↑
LPIPS ↓
MAE (m) ↓
RMSE (m) ↓
Base Model
28.851
0.882
0.189
0.922
1.727
TSDF
28.994
0.898
0.157
0.543
1.161
w/o PatchMatch
29.341
0.899
0.161
0.579
1.133
SfM Initialization
28.860
0.882
0.189
0.599
1.165
Full Model
28.994
0.898
0.157
0.512
1.047
Table 3: Ablation of PatchMatch supervision, Delaunay graph-cut meshing, and dense point cloud initialization. We report visual metrics and geometric metrics.