In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting

Wenhui Xiao; Ethan Goan; Rodrigo Santa Cruz; David Ahmedt-Aristizabal; Olivier Salvado; Clinton Fookes; Leo Lebrat

cs.CVApr 7, 2026

In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting

Authors: Wenhui Xiao, Ethan Goan, Rodrigo Santa Cruz, David Ahmedt-Aristizabal, Olivier Salvado, Clinton Fookes, Leo Lebrat

Organizations: Queensland University of Technology · CSRIO Data61

Abstract

Using accurate depth priors in 3D Gaussian Splatting helps mitigate artifacts caused by sparse training data and textureless surfaces. However, acquiring accurate depth maps requires specialized acquisition systems. Foundation monocular depth estimation models offer a cost-effective alternative, but they suffer from scale ambiguity, multi-view inconsistency, and local geometric inaccuracies, which can degrade rendering performance when applied naively. This paper addresses the challenge of reliably leveraging monocular depth priors for Gaussian Splatting (GS) rendering enhancement. To this end, we introduce a training framework integrating scale-ambiguous and noisy depth priors into geometric supervision. We highlight the importance of learning from weakly aligned depth variations. We introduce a method to isolate ill-posed geometry for selective monocular depth regularization, restricting the propagation of depth inaccuracies into well-reconstructed 3D structures. Extensive experiments across diverse datasets show consistent improvements in geometric accuracy, leading to more faithful depth estimation and higher rendering quality across different GS variants and monocular depth backbones tested.

Figures & tables

Figure 2: Impact of SfM point count in scale alignment on GS rendering quality for identical training images and point clouds. When using only $\mathcal{L}_{\text{sid}}$ , fewer observed points lead to degraded performance compared to the baseline (without using monocular depth supervision), highlighting the limitation of scale-invariant depth supervision in aligning monocular depth cues.

Figure 3: Overview of our proposed framework. During GS optimization, depth-inconsistent Gaussians are identified using a virtual stereo setup ( Sec. 4.1 ). These regions guide the learning of absolute depth corrections from monocular depth priors aligned with sparse SfM point clouds. Additionally, a relative depth loss ( Sec. 4.2 ) is applied to learn geometric cues under ambiguous scene scales.

Figure 4: Comparison of different relative depth supervision losses, shown on two zoomed-in scene crops. Gradient-based loss ( GAL ) achieves sharper rendering with fewer smearing artifacts compared to the patch-based Pearson correlation loss, as seen in the reduced distortion on photo-frame edges in the top row and a clearer shape around the orange triangular region in the bottom.

		Low Data				Moderate Data
		PSNR ↑	SSIM ↑	LPIPS ↓	AVG-E ↓	PSNR ↑	SSIM ↑	LPIPS ↓	AVG-E ↓
3DGS [ 19 ]	3DGS (w/o depth)	19.916	0.7206	0.2715	0.1156	23.240	0.8158	0.1920	0.0747
	SparseGS [ 42 ]	20.152	0.7202	0.2719	0.1134	23.146	0.8091	0.2133	0.0783
	DNGaussian [ 23 ]	19.740	0.6905	0.3717	0.1314	22.190	0.7634	0.3017	0.0976
	FSGS [ 49 ]	20.307	0.7213	0.3069	0.1165	22.998	0.7949	0.254	0.085
	$\mathcal{L}_{\text{sid}}$	20.173	0.7208	0.2721	0.1132	23.318	0.8149	0.1941	0.0747

Table 2: Results on the TanksAndTemples. Best performance is bolded in red and the second is marked in orange .

		Low Data				Moderate Data
		PSNR ↑	SSIM ↑	LPIPS ↓	AVG-E ↓	PSNR ↑	SSIM ↑	LPIPS ↓	AVG-E ↓
3DGS [ 19 ]	3DGS (w/o depth)	21.785	0.6267	0.3409	0.1210	25.591	0.7576	0.2513	0.0751
	SparseGS [ 42 ]	22.015	0.6302	0.3462	0.1192	25.519	0.7570	0.2590	0.0762
	DNGaussian [ 23 ]	21.801	0.6054	0.4594	0.1314	24.245	0.6789	0.3962	0.1002
	FSGS [ 49 ]	21.693	0.6120	0.4186	0.1293	24.811	0.6997	0.358	0.093
	$\mathcal{L}_{\text{sid}}$	21.799	0.6274	0.3399	0.1202	25.668	0.7586	0.2501	0.0745

Table 3: Results on the MipNeRF 360. Best performance is bolded in red and the second is marked in orange .

Figure 5: Qualitative results on 3DGS . ( Top ): low-data setting; ( Bottom ): moderate-data setting.

Figure 6: Qualitative comparisons of rendered images and depth maps on the ScanNet++ dataset for the baseline (without depth supervision), $\mathcal{L}_{\text{sid}}$ , and our method using MoGe-2 monocular depth supervision. Our method produces clearer, more accurate depth maps and yields sharper, less artifact-prone renderings than the baseline and $\mathcal{L}_{\text{sid}}$ . We encourage readers to zoom in for a clearer visual comparison.

$\mathcal{L}_{\text{sid}}$	DIM	GAL	PSNR ↑	SSIM ↑	LPIPS ↓	AVG-E ↓
✓			21.42	0.620	0.348	0.127
✓	✓		21.66	0.624	0.346	0.123
✓	✓	✓	22.09	0.639	0.354	0.118

Table 4: Module ablation study on all scenes of the MipNeRF 360 dataset. The best performance is bolded .

Scene	Method	PSNR ↑	SSIM ↑	LPIPS ↓	AVG-E ↓	Train(min)
Outdoor	NCC ${}_{\text{w63}}$	18.60	0.449	0.423	0.167	26.76
	NCC ${}_{\text{w127}}$	18.56	0.447	0.421	0.168	37.39
	$\mathcal{L}_{\text{cosine}}$	18.09	0.430	0.425	0.175	22.5
	Ours	18.97	0.464	0.430	0.163	21.52
Indoor	NCC ${}_{\text{w63}}$	25.47	0.851	0.263	0.066	30.59
	NCC ${}_{\text{w127}}$	25.98	0.858	0.254	0.063	47.23

Table 5: Comparisons of different relative depth loss choices on MipNeRF 360. The best performance is bolded .

3D Gaussian Splatting

3D Gaussian Splatting represents scenes as optimizable 3D Gaussian primitives for fast, photorealistic rendering from new viewpoints.

See all 1,019 papers

2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction
May 1, 2026Prajwal Gupta C. R., Divyam Sheth, Jinjoo Ha +23D Gaussian Splatting 3D Reconstruction
TU Darmstadt · ELIZA · Max Planck Institute for Intelligent Systems
Prior-Driven Enhancements in 3D Gaussian Splatting: Normals and Depths Regularization
Sep 29, 2026Gyeonggwan Lee, Seunghwan Hong, Junghun Suh3D Gaussian Splatting 3D Reconstruction
AI R&D Team, KakaoMobility, Korea
Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction
Jun 27, 2026Wei-Teng Chu, Yashasvini Gopalan, Changju YuanSparse-View 3D Reconstruction Neural Radiance Fields
Stanford University

May 1, 2026J/K move · Enter open · S save

2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction

Prajwal Gupta C. R., Divyam Sheth, Jinjoo Ha, Mirela Ostrek+1

TU Darmstadt · ELIZA · Max Planck Institute for Intelligent Systems

3D Gaussian Splatting 3D Reconstruction Multi-View 3D Reconstruction 3D Mesh Reconstruction

Open paper AskPDF arXiv

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address this, 2D Gaussian Splatting (2DGS) was proposed to enable view-consistent and geometrically accurate surface reconstruction from multi-view images. However, 2DGS can be sensitive to the initialization of the Gaussian primitives. Reliance on Structure-from-Motion (SfM) initializations, which can produce poor estimates on challenging image sets, may lead to subpar results. In this work, we enhance 2DGS by incorporating monocular depth and normal priors to improve both geometric accuracy and robustness. We propose a depth-guided initialization strategy for Gaussians and introduce a clustering-based technique for pruning degenerate Gaussians. We evaluate our method on the DTU dataset, where it achieves state-of-the-art results in mesh reconstruction while preserving high-quality novel view synthesis.

Abstract

3D Gaussian Splatting

Explore similar work

2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction

Prior-Driven Enhancements in 3D Gaussian Splatting: Normals and Depths Regularization

Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction