RecGS: Removing Water Caustic with Recurrent Gaussian Splatting

TL;DR

RecGS is a novel 3D reconstruction-based method that effectively removes water caustics from seafloor images, outperforming traditional filtering and deep learning approaches by leveraging recurrent 3D modeling.

Contribution

The paper introduces RecGS, a new method that uses recurrent 3D Gaussian splatting to separate caustics from underwater images, enhancing visual quality without relying on extensive training data.

Findings

RecGS effectively removes caustics and improves image clarity.

Compared to other methods, RecGS shows superior performance in experiments.

The approach has potential applications in various illumination-inconsistent scenarios.

Abstract

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.