GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field
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_ | 1866908368332914688 |
|---|---|
| author | Lu, Zuxing Yuan, Xin Yang, Shaowen Liu, Jingyu Sun, Changyin |
| author_facet | Lu, Zuxing Yuan, Xin Yang, Shaowen Liu, Jingyu Sun, Changyin |
| contents | Semantic-aware 3D scene reconstruction is essential for autonomous robots to perform complex interactions. Semantic SLAM, an online approach, integrates pose tracking, geometric reconstruction, and semantic mapping into a unified framework, shows significant potential. However, existing systems, which rely on 2D ground truth priors for supervision, are often limited by the sparsity and noise of these signals in real-world environments. To address this challenge, we propose GSFF-SLAM, a novel dense semantic SLAM system based on 3D Gaussian Splatting that leverages feature fields to achieve joint rendering of appearance, geometry, and N-dimensional semantic features. By independently optimizing feature gradients, our method supports semantic reconstruction using various forms of 2D priors, particularly sparse and noisy signals. Experimental results demonstrate that our approach outperforms previous methods in both tracking accuracy and photorealistic rendering quality. When utilizing 2D ground truth priors, GSFF-SLAM achieves state-of-the-art semantic segmentation performance with 95.03\% mIoU, while achieving up to 2.9$\times$ speedup with only marginal performance degradation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field Lu, Zuxing Yuan, Xin Yang, Shaowen Liu, Jingyu Sun, Changyin Robotics Artificial Intelligence Semantic-aware 3D scene reconstruction is essential for autonomous robots to perform complex interactions. Semantic SLAM, an online approach, integrates pose tracking, geometric reconstruction, and semantic mapping into a unified framework, shows significant potential. However, existing systems, which rely on 2D ground truth priors for supervision, are often limited by the sparsity and noise of these signals in real-world environments. To address this challenge, we propose GSFF-SLAM, a novel dense semantic SLAM system based on 3D Gaussian Splatting that leverages feature fields to achieve joint rendering of appearance, geometry, and N-dimensional semantic features. By independently optimizing feature gradients, our method supports semantic reconstruction using various forms of 2D priors, particularly sparse and noisy signals. Experimental results demonstrate that our approach outperforms previous methods in both tracking accuracy and photorealistic rendering quality. When utilizing 2D ground truth priors, GSFF-SLAM achieves state-of-the-art semantic segmentation performance with 95.03\% mIoU, while achieving up to 2.9$\times$ speedup with only marginal performance degradation. |
| title | GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2504.19409 |