RecGS：利用递归高斯溅射去除水中焦散
RecGS: Removing Water Caustic with Recurrent Gaussian Splatting
AI总结：
针对浅水海底图像中的水焦散干扰，提出基于递归高斯溅射（RecGS）的三维重建与低通滤波迭代分解方法，有效分离焦散并提升视觉质量。
摘要：
水焦散现象常见于浅水区域的海底成像数据中。传统的从图像中去除焦散图案的方法通常依赖于二维滤波或在带标注的数据集上进行预训练，这阻碍了其泛化到具有三维结构的真实海底数据时的性能。本文提出了一种新颖的方法——递归高斯溅射（RecGS），利用当今逼真的三维重建技术3DGS，将焦散与海底图像分离。利用水下机器人拍摄的一系列图像，我们递归地构建3DGS，并在每次迭代中通过低通滤波分解焦散。在实验中，我们分析并比较了不同方法，包括联合优化、二维滤波和深度学习方法。结果表明，我们的方法能有效将焦散从海底分离，改善视觉外观，并可能应用于更多光照不一致的问题。
英文摘要：
Water caustics are commonly observed in seafloor imaging data from shallow-water areas. Traditional methods that remove caustic patterns from images often rely on 2D filtering or pre-training on an annotated dataset, hindering the performance when generalizing to real-world seafloor data with 3D structures. In this paper, we present a novel method Recurrent Gaussian Splatting (RecGS), which takes advantage of today's photorealistic 3D reconstruction technology, 3DGS, to separate caustics from seafloor imagery. With a sequence of images taken by an underwater robot, we build 3DGS recurrently and decompose the caustic with low-pass filtering in each iteration. In the experiments, we analyze and compare with different methods, including joint optimization, 2D filtering, and deep learning approaches. The results show that our method can effectively separate the caustic from the seafloor, improving the visual appearance, and can be potentially applied on more problems with inconsistent illumination.
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。
