WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment
This addresses the challenge of underwater SLAM for applications like autonomous vehicles and marine archaeology, representing an incremental improvement with specific gains.
The paper tackles the problem of producing high-fidelity maps in underwater monocular SLAM, achieving robust pose estimation and photorealistic dense mapping through semantic medium filtering and adaptive rendering strategies.
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.