GS-2M: Material-aware Gaussian Splatting for High-fidelity Mesh Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910044470116352 |
|---|---|
| author | Nguyen, Dinh Minh Avenhaus, Malte Lindemeier, Thomas |
| author_facet | Nguyen, Dinh Minh Avenhaus, Malte Lindemeier, Thomas |
| contents | We propose a material-aware optimization framework for high-fidelity mesh reconstruction from multi-view images based on 3D Gaussian Splatting, referred to as GS-2M. Previous works handle these tasks separately and struggle to reconstruct highly reflective surfaces, often relying on priors from external models to enhance the decomposition results. Conversely, our method addresses these two problems by jointly optimizing attributes relevant to the quality of rendered depth and normals, maintaining geometric details while being resilient to reflective surfaces. Although contemporary works effectively solve these tasks together, they often employ sophisticated neural components to learn scene properties, which hinders their performance at scale. To further eliminate these neural components, we propose a novel roughness supervision strategy based on multi-view photometric variation. When combined with a carefully designed loss and optimization process, our unified framework produces reconstruction results comparable to state-of-the-art methods, delivering accurate triangle meshes even for reflective surfaces. We validate the effectiveness of our approach with widely used datasets from previous works and qualitative comparisons with state-of-the-art surface reconstruction methods. Project page: https://ndming.github.io/publications/gs2m/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22276 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GS-2M: Material-aware Gaussian Splatting for High-fidelity Mesh Reconstruction Nguyen, Dinh Minh Avenhaus, Malte Lindemeier, Thomas Computer Vision and Pattern Recognition We propose a material-aware optimization framework for high-fidelity mesh reconstruction from multi-view images based on 3D Gaussian Splatting, referred to as GS-2M. Previous works handle these tasks separately and struggle to reconstruct highly reflective surfaces, often relying on priors from external models to enhance the decomposition results. Conversely, our method addresses these two problems by jointly optimizing attributes relevant to the quality of rendered depth and normals, maintaining geometric details while being resilient to reflective surfaces. Although contemporary works effectively solve these tasks together, they often employ sophisticated neural components to learn scene properties, which hinders their performance at scale. To further eliminate these neural components, we propose a novel roughness supervision strategy based on multi-view photometric variation. When combined with a carefully designed loss and optimization process, our unified framework produces reconstruction results comparable to state-of-the-art methods, delivering accurate triangle meshes even for reflective surfaces. We validate the effectiveness of our approach with widely used datasets from previous works and qualitative comparisons with state-of-the-art surface reconstruction methods. Project page: https://ndming.github.io/publications/gs2m/. |
| title | GS-2M: Material-aware Gaussian Splatting for High-fidelity Mesh Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22276 |