RecGS: Removing Water Caustic with Recurrent Gaussian Splatting
This addresses the issue of caustic removal in underwater imaging for marine robotics and environmental monitoring, but it is incremental as it builds on existing 3DGS technology.
The paper tackles the problem of removing water caustics from seafloor imagery, which is challenging due to 3D structures, by proposing RecGS, a method that uses recurrent Gaussian splatting to separate caustics, improving visual appearance and showing potential for broader applications with inconsistent illumination.
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.