arXiv 2604.046422026-04-06cs.RO

WaterSplat-SLAM：水下环境中的光实单目SLAM

WaterSplat-SLAM: Photorealistic Monocular SLAM in Underwater Environment

Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Key Laboratory of Marine Robotics, Shenyang（沈阳海洋机器人重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（香港科技大学电子及计算机工程学系）

Kangxu Wang, Shaofeng Zou, Chenxing Jiang, Yixiang Dai, Siang Chen, Shaojie Shen, Guijin Wang

备注：: 8 pages, 6 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出WaterSplat-SLAM，通过语义介质过滤和语义引导渲染实现水下高保真密集映射，提升水下单目SLAM的鲁棒性与可视化效果。

摘要：

水下单目SLAM是一个具有广泛应用的挑战性问题，从自主水下车辆到海洋考古均有涉及。然而，现有水下SLAM方法难以生成高保真的地图。本文提出WaterSplat-SLAM，一种新的水下单目SLAM系统，实现稳健的位姿估计和光实密集映射。具体而言，我们将语义介质过滤引入两视角3D重建之前，以实现适应水下环境的相机跟踪和深度估计。此外，我们还提出一种语义引导的渲染和自适应地图管理策略，结合在线介质感知高斯地图，以光实且紧凑的方式建模水下环境。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稳健的相机跟踪和高保真的渲染。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。