提出水下单目SLAM新方法，实现高保真建图与稳定定位。
WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment
- 引入语义介质滤波，提升水下相机跟踪与深度估计精度。
- 基于语义引导的自适应高斯地图，实现紧凑且逼真的三维重建。
- 适用于水下机器人、海洋考古等需要高真实感地图的场景。
水下单目SLAM在自主水下航行器、海洋考古等领域具有重要应用，但现有方法难以生成高保真渲染地图。本文提出WaterSplat-SLAM，一种新型单目水下SLAM系统，实现了鲁棒的位姿估计与高保真稠密建图。具体而言，我们在两视图3D重建前引入语义介质滤波，以适配水下环境的相机跟踪与深度估计。此外，提出一种语义引导的渲染与自适应地图管理策略，结合在线介质感知的高斯地图，实现水下环境的逼真且紧凑的建模。在多个水下数据集上的实验表明，WaterSplat-SLAM在水下环境中实现了鲁棒的相机跟踪与高保真渲染。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。