GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction

TL;DR

This work proposes GSM-GS: a synergistic optimization framework integrating single-view adaptive sub-region weighting constraints and multi-view spatial structure refinement, which achieves both competitive rendering quality and geometric reconstruction.

Abstract

Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses challenges to reconstruction accuracy. This limitation frequently causes high-frequency detail loss in complex surface microstructures when relying solely on routine strategies. To address this limitation, we propose GSM-GS: a synergistic optimization framework integrating single-view adaptive sub-region weighting constraints and multi-view spatial structure refinement. For single-view optimization, we leverage image gradient features to partition scenes into texture-rich and texture-less sub-regions. The reconstruction quality is enhanced through adaptive filtering mechanisms guided by depth discrepancy features. This preserves high-weight regions while implementing a dual-branch constraint strategy tailored to regional texture variations, thereby improving geometric detail characterization. For multi-view optimization, we introduce a geometry-guided cross-view point cloud association method combined with a dynamic weight sampling strategy. This constructs 3D structural normal constraints across adjacent point cloud frames, effectively reinforcing multi-view consistency and reconstruction fidelity. Extensive experiments on public datasets demonstrate that our method achieves both competitive rendering quality and geometric reconstruction. See our interactive project page

Figures (15)

• Figure 1: Spatial distribution comparison of Gaussian ellipsoids. This figure compares the spatial ellipsoid distributions reconstructed by the 3DGS, PGSR, and Ours algorithms for the rendered scene. The 3DGS results exhibit suboptimal performance, as their Gaussian ellipsoids fail to conform closely to object surfaces. While both PGSR and ours employ thin Gaussian ellipsoids for surface approximation, our method introduces novel constraints derived from single-view and multi-view paradigms. This optimization yields more regular ellipsoid distributions and significantly enhanced surface conformity.
• Figure 2: GSM-GS Overview. The algorithm framework takes sparse point cloud data and image input, initializes each point cloud into a thin Gaussian ellipsoid, and processes a single-view adaptive partitioning constraint, dual-branch optimization strategy, weight-guided dynamic sampling strategy, and cross-view geometric correlation normal constraint. The system is innovatively optimized from the perspectives of single-view and multi-view, and finally outputs high-quality reconstruction and rendering results.
• Figure 3: Filtering trust regions based on converting the difference between rendering depth and weight information. (a) is the RGB map of the real scene; (b) the difference between the rendering depth and the unbiased depth is used to calculate the difference, and then the difference is converted into weight information to reflect the reconstruction effect of each point in the scene; (c) the scene is partitioned using the weight information, and the low weight part is filtered out(the bright part of the map), and the low weight part is filtered out(the darker region of the map), and the data of the trust region is prioritized to added into the system for computation in the subsequent regularization. The data from the trusted regions is prioritized in the subsequent regularisation and added to the system for computation.
• Figure 4: Calculate the gradient of the original image and classify the scene into texture-rich and texture-less regions according to the threshold. (a) Original RGB image. (b) Calculated gradient of the image, with the blue bias representing a flatter gradient region and the white bias a higher gradient region. (c) According to the threshold screening, the red part is a texture-rich region and the blue part is a texture-less region.
• Figure 5: Analysis of reconstruction results based on normal maps. (a) Ground-truth RGB image; (b) Normal map reconstructed by the baseline PGSR algorithm; (c) Normal map reconstructed using the proposed single-view constrained optimization strategy. Comparative results demonstrate that our method yields more accurate geometric reconstruction than the baseline, particularly in preserving fine-grained details of real-world scenes.