GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913819461156864 |
|---|---|
| author | Su, Yongxin Chen, Lin Zhang, Kaiting Zhao, Zhongliang Hou, Chenfeng Yu, Ziping |
| author_facet | Su, Yongxin Chen, Lin Zhang, Kaiting Zhao, Zhongliang Hou, Chenfeng Yu, Ziping |
| contents | We propose GauS-SLAM, a dense RGB-D SLAM system that leverages 2D Gaussian surfels to achieve robust tracking and high-fidelity mapping. Our investigations reveal that Gaussian-based scene representations exhibit geometry distortion under novel viewpoints, which significantly degrades the accuracy of Gaussian-based tracking methods. These geometry inconsistencies arise primarily from the depth modeling of Gaussian primitives and the mutual interference between surfaces during the depth blending. To address these, we propose a 2D Gaussian-based incremental reconstruction strategy coupled with a Surface-aware Depth Rendering mechanism, which significantly enhances geometry accuracy and multi-view consistency. Additionally, the proposed local map design dynamically isolates visible surfaces during tracking, mitigating misalignment caused by occluded regions in global maps while maintaining computational efficiency with increasing Gaussian density. Extensive experiments across multiple datasets demonstrate that GauS-SLAM outperforms comparable methods, delivering superior tracking precision and rendering fidelity. The project page will be made available at https://gaus-slam.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01934 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels Su, Yongxin Chen, Lin Zhang, Kaiting Zhao, Zhongliang Hou, Chenfeng Yu, Ziping Computer Vision and Pattern Recognition We propose GauS-SLAM, a dense RGB-D SLAM system that leverages 2D Gaussian surfels to achieve robust tracking and high-fidelity mapping. Our investigations reveal that Gaussian-based scene representations exhibit geometry distortion under novel viewpoints, which significantly degrades the accuracy of Gaussian-based tracking methods. These geometry inconsistencies arise primarily from the depth modeling of Gaussian primitives and the mutual interference between surfaces during the depth blending. To address these, we propose a 2D Gaussian-based incremental reconstruction strategy coupled with a Surface-aware Depth Rendering mechanism, which significantly enhances geometry accuracy and multi-view consistency. Additionally, the proposed local map design dynamically isolates visible surfaces during tracking, mitigating misalignment caused by occluded regions in global maps while maintaining computational efficiency with increasing Gaussian density. Extensive experiments across multiple datasets demonstrate that GauS-SLAM outperforms comparable methods, delivering superior tracking precision and rendering fidelity. The project page will be made available at https://gaus-slam.github.io. |
| title | GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.01934 |