DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction
Authors: Xiao Ren, Yu Liu, Ning An, Jian Cheng, Xin Qiao, You-Fu Li, He Kong
Organizations: School of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518055, China · Research Institute of Mine Artificial Intelligence, China Coal Research Institute, and the State Key Laboratory of Intelligent Coal Mining and Strata Control, Beijing 100031, China · Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China · Department of Mechanical Engineering, City University of Hong Kong, Hong Kong SAR, China
Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient representation for novel view synthesis, offering fast differentiable rendering and high visual fidelity, and has increasingly been extended to surface reconstruction. However, the relationship between depth information and reconstruction error remains insufficiently explored, limiting the principled design of geometric optimization strategies. To fill the above gap, we propose DepthGS, a depth-guided Gaussian splatting framework. We derive theoretical relations between depth discrepancies and reconstruction error under single-view and multi-view settings, and rigorously establish corresponding upper bounds on reconstruction error. The above analysis informs the design of adaptive regularization strategies in both single-view and multi-view optimization. More specifically, for single-view optimization, we propose a depth-difference-guided adaptive normal regularization strategy that modulates the normal constraint strength using a geometric reliability weight computed from local depth differences. For multi-view optimization, we introduce a cross-view depth consistency regularization strategy that promotes consistency between neighboring-view depth maps and the corresponding depth predictions obtained by transforming the current view's depth predictions into those neighboring views. Extensive experiments on DTU, Mip-NeRF360, and Tanks and Temples demonstrate that DepthGS achieves competitive performance in both surface reconstruction and novel view synthesis.
Figures & tables
Fig. 1: Overview of the proposed framework. The Gaussian representation is initialized from a sparse point cloud and used to render the distance and normal maps. Unbiased depth maps are then derived from these rendered quantities. The discrepancy between the unbiased depth and rendered distance is used to compute the depth-difference-based weight WΔD , which modulates the single-view normal constraint Lsvgeo . In the multi-view branch, coordinate transformations establish depth correspondences between neighboring views to construct the cross-view depth consistency constraint Lmv_D . The proposed constraints are jointly optimized with the baseline objectives to improve surface reconstruction and multi-view geometric consistency.
Fig. 2: Depth differences (left) and corresponding Gaussian distributions (right); large discrepancies often coincide with irregular Gaussian layouts.
Fig. 3: Depth-difference weights are derived from the discrepancy between the rendered-distance map and the unbiased-depth map. The greater the depth difference, the smaller the weight.
Fig. 4: Comparison of N(p)⋅v(p) obtained by PGSR and the proposed method. The proposed method generally yields normal–ray consistency values closer to 1 in the evaluated scenes.
Fig. 5: Cross-view inconsistency of depth-difference maps at corresponding surface locations in neighboring views.
Method
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
Time
NeRF [ 10 ]
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
> 12h
VolSDF [ 44 ]
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
> 12h
NeuS [ 45 ]
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
> 12h
2DGS [ 36 ]
0.48
0.82
0.34
0.43
1.35
0.90
0.81
1.27
1.24
0.65
0.70
1.25
0.41
0.66
0.50
0.79
8.5min
GOF [ 37 ]
0.50
0.83
0.40
0.38
1.35
0.82
0.74
1.26
1.79
0.69
0.71
1.31
0.52
0.64
0.51
0.83
33min
GFSGS [ 38 ]
0.38
0.65
0.29
0.36
0.79
0.65
0.64
1.09
1.21
0.59
0.47
1.19
0.32
0.42
0.37
0.63
9.9min
TABLE I: Quantitative reconstruction accuracy on DTU measured by Chamfer distance (mm) ↓ . In the CD columns, red, orange, and yellow indicate the best, second-best, and third-best results, respectively. The superscript † denotes results reproduced by us.
Fig. 6: Qualitative surface reconstruction comparison on the DTU dataset. Reconstructed meshes and zoom-in regions are shown to compare local surface details and geometric completeness across different methods.
Fig. 7: Qualitative surface reconstruction comparison on the Tanks and Temples dataset. Reconstructed meshes and zoom-in regions are shown to compare local surface continuity and geometric details across different methods.
Fig. 8: Qualitative comparison on the Mip-NeRF360 dataset. Rendered images from different methods are shown with enlarged local regions marked by red boxes. The results suggest that our method preserves fine image details and local structures in the selected scenes.
Method
Outdoor scenes
Indoor scenes
Overall average
SSIM ↑
PSNR ↑
LPIPS ↓
SSIM ↑
PSNR ↑
LPIPS ↓
SSIM ↑
PSNR ↑
LPIPS ↓
3DGS [ 13 ]
0.742
25.07
0.232
0.931
31.18
0.164
0.837
28.13
0.198
2DGS [ 36 ]
0.706
24.21
0.284
0.912
30.15
0.212
0.809
27.18
0.248
GOF [ 37 ]
0.746
24.81
0.208
0.917
30.40
0.189
0.832
27.61
0.199
GFSGS [ 38 ]
0.734
24.40
0.224
0.916
29.93
0.194
0.825
27.17
0.209
GS-UDF [ 41 ]
0.698
23.84
0.292
0.906
29.16
0.219
0.802
26.50
0.255
TABLE III: Novel-view-synthesis results on Mip-NeRF360. Red, orange, and yellow indicate the best, second-best, and third-best results, respectively; † denotes reproduced results.
Fig. 9: Optimization dynamics compared with PGSR. (a) Training- and test-view PSNR curves; (b) per-iteration ΔPSNR ; (c) average training- and test-view PSNR.
Fig. 10: Novel-view-synthesis ablation results. The rows show RGB, unbiased depth, and normal maps; the columns show PGSR, the two individual components, and the full model.
WΔD
Lmv_D
PSNR ↑
SSIM ↑
LPIPS ↓
×
×
27.45
0.841
0.181
✓
×
27.75
0.842
0.175
×
✓
27.51
0.842
0.180
✓
✓
27.73
0.841
0.175
TABLE IV: Ablation study on the Mip-NeRF360 dataset. Best results are in bold.
Method
WΔD
Lmv_D
CD ↓
Avg. Mem. ↓
Peak Mem. ↓
PGSR
×
×
0.53
6.41
7.12
+ Lmv_D
×
✓
0.52
6.89
7.98
+ WΔD
✓
×
0.51
6.74
7.43
Ours
✓
✓
0.51
6.77
7.50
TABLE V: Ablation study on the DTU dataset (CD: mm; memory: GB).
Fig. 11: 3D reconstruction ablation study. The red dashed box indicates the magnified region. The comparison of local structures within the highlighted region illustrates the effects of different components on local contour preservation and geometric details.
Fig. 12: Mean EMVC on DTU and Mip-NeRF360. Shaded regions denote standard errors across scenes.
3D reconstruction from sparse views is a challenging task in 3D computer vision. Recent studies on 3D Gaussian Splatting (3DGS) have achieved remarkable results with sparse views in novel view synthesis, yet reconstructing high-quality geometric surfaces from sparse views remains a challenge, due to the limited geometry clues and the discreteness of Gaussians. In this paper, we propose a novel 3DGS-based method for high-fidelity surface reconstruction from sparse views. Our key insight is to introduce a normal-guided depth propagation approach, which can extend depth information from high-confidence regions to constrain the depth in low-confidence areas. Additionally, we propose an abnormal depth edge-aware regularization to address depth discontinuities caused by the discreteness of Gaussians. Extensive experiments on DTU and Tanks-and-Temples datasets demonstrate that our method outperforms the state-of-the-art methods in sparse view surface reconstruction. Project page: https://hanl2010.github.io/DP-GS.
Liang Han, Bangcai Wei, Junsheng Zhou +2
School of Software, Tsinghua University, Beijing, China · China Telecom · Department of Computer Science, Wayne State University, Detroit, USA
Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and missing details in under-constrained regions, resulting in degraded reconstruction and unstable rendering. To tackle these issues, we propose D3GS, a Depth-DINO-Diffusion guided sparse-view Gaussian reconstruction framework that jointly enhances geometry and appearance. D3GS first recovers a high-resolution, metric depth map via diffusion-based completion and DPT (Dense Prediction Transformer) refinement, providing robust Gaussian initialization and geometric constraints. Then, a DINO-guided view-consistent learning is introduced to augment Gaussian attributes with structural features, improving multi-view consistency. Finally, a diffusion-based Gaussian refinement module injects generative priors into an iterative optimization strategy, enhancing high-frequency geometric and appearance details within the Gaussian representation. Experiments on DTU, LLFF, and Mip-NeRF 360 show that D3GS achieves consistent and substantial improvements over strong baselines, with ablation studies validating the effectiveness and complementary roles of each component.
Yunqi Gao, Zhanfeng Liao, Hanzhang Tu +7
Central China Normal University · Tsinghua University · Fuzhou University +4
Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread and shapes, such as 2D Gaussian Splatting, have significantly improved geometric fidelity. In this paper, we present Pixel-Aligned 1DoF Gaussian Splatting (PAGaS) that adapts the GS representation from novel view synthesis to the multi-view stereo depth task. Our key contribution is modeling a pixel's depth using one-degree-of-freedom (1DoF) Gaussians that remain tightly constrained during optimization. Unlike existing approaches, our Gaussians' positions and sizes are restricted by the back-projected pixel volumes, leaving depth as the sole degree of freedom to optimize. PAGaS produces highly detailed depths, as illustrated in Figure 1. We quantitatively validate these improvements on top of reference geometric and learning-based multi-view stereo baselines on challenging 3D reconstruction benchmarks. Code: davidrecasens.github.io/pagas