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.
@article{arxiv.2604.04642,
title = {WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment},
author = {Kangxu Wang and Shaofeng Zou and Chenxing Jiang and Yixiang Dai and Siang Chen and Shaojie Shen and Guijin Wang},
journal= {arXiv preprint arXiv:2604.04642},
year = {2026}
}