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

TL;DR

GSM-GS enhances 3D Gaussian Splatting for surface reconstruction by integrating texture-aware single-view and multi-view constraints, significantly improving geometric detail preservation and multi-view consistency.

Contribution

It introduces a novel optimization framework combining adaptive regional weighting and geometry-guided multi-view constraints for improved surface reconstruction.

Findings

Achieves high-fidelity rendering comparable to state-of-the-art methods.

Effectively preserves high-frequency surface details in complex microstructures.

Demonstrates improved multi-view consistency and reconstruction accuracy.

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