GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910021198020608 |
|---|---|
| author | Ren, Xiao Liu, Yu An, Ning Cheng, Jian Qiao, Xin Kong, He |
| author_facet | Ren, Xiao Liu, Yu An, Ning Cheng, Jian Qiao, Xin Kong, He |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12796 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction Ren, Xiao Liu, Yu An, Ning Cheng, Jian Qiao, Xin Kong, He Computer Vision and Pattern Recognition Graphics 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 |
| title | GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2602.12796 |