WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908939978801152 |
|---|---|
| author | Wang, Kangxu Zou, Shaofeng Jiang, Chenxing Dai, Yixiang Chen, Siang Shen, Shaojie Wang, Guijin |
| author_facet | Wang, Kangxu Zou, Shaofeng Jiang, Chenxing Dai, Yixiang Chen, Siang Shen, Shaojie Wang, Guijin |
| contents | Underwater monocular SLAM is a challenging problem with applications from autonomous underwater vehicles to marine archaeology. However, existing underwater SLAM methods struggle to produce maps with high-fidelity rendering. In this paper, we propose WaterSplat-SLAM, a novel monocular underwater SLAM system that achieves robust pose estimation and photorealistic dense mapping. Specifically, we couple semantic medium filtering into two-view 3D reconstruction prior to enable underwater-adapted camera tracking and depth estimation. Furthermore, we present a semantic-guided rendering and adaptive map management strategy with an online medium-aware Gaussian map, modeling underwater environment in a photorealistic and compact manner. Experiments on multiple underwater datasets demonstrate that WaterSplat-SLAM achieves robust camera tracking and high-fidelity rendering in underwater environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04642 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment Wang, Kangxu Zou, Shaofeng Jiang, Chenxing Dai, Yixiang Chen, Siang Shen, Shaojie Wang, Guijin Robotics Underwater monocular SLAM is a challenging problem with applications from autonomous underwater vehicles to marine archaeology. However, existing underwater SLAM methods struggle to produce maps with high-fidelity rendering. In this paper, we propose WaterSplat-SLAM, a novel monocular underwater SLAM system that achieves robust pose estimation and photorealistic dense mapping. Specifically, we couple semantic medium filtering into two-view 3D reconstruction prior to enable underwater-adapted camera tracking and depth estimation. Furthermore, we present a semantic-guided rendering and adaptive map management strategy with an online medium-aware Gaussian map, modeling underwater environment in a photorealistic and compact manner. Experiments on multiple underwater datasets demonstrate that WaterSplat-SLAM achieves robust camera tracking and high-fidelity rendering in underwater environments. |
| title | WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.04642 |