# RecGS: Removing Water Caustic with Recurrent Gaussian Splatting

arXiv: https://arxiv.org/abs/2407.10318 · HTML: https://mlsanity.com/paper/2407.10318/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 14 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Physics-informed neural networks (PINNs) for fluid mechanics: A review](https://mlsanity.com/paper/2105.09506/) (2021)
- [GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces](https://mlsanity.com/paper/2311.17977/) (2023)
- [DeepSFM: Structure From Motion Via Deep Bundle Adjustment](https://mlsanity.com/paper/1912.09697/) (2019)
- [Bilateral Guided Radiance Field Processing](https://mlsanity.com/paper/2406.00448/) (2024)
- [DarkGS: Learning Neural Illumination and 3D Gaussians Relighting for Robotic Exploration in the Dark](https://mlsanity.com/paper/2403.10814/) (2024)
- [Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery](https://mlsanity.com/paper/2304.03384/) (2023)
- [Parallelised Diffeomorphic Sampling-based Motion Planning](https://mlsanity.com/paper/2108.11775/) (2021)
- [Robust Gaussian Splatting](https://mlsanity.com/paper/2404.04211/) (2024)
- [V-PRISM: Probabilistic Mapping of Unknown Tabletop Scenes](https://mlsanity.com/paper/2403.08106/) (2024)
- [Customizable Perturbation Synthesis for Robust SLAM Benchmarking](https://mlsanity.com/paper/2402.08125/) (2024)
- [Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization](https://mlsanity.com/paper/2109.04087/) (2021)
- [Seafloor-Invariant Caustics Removal from Underwater Imagery](https://mlsanity.com/paper/2212.10167/) (2022)
- [Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models](https://mlsanity.com/paper/2404.11683/) (2024)

## Built on by (most cited first, 16 of 16)

- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting](https://mlsanity.com/paper/2410.06014/) (2024)
- [OceanSim: A GPU-Accelerated Underwater Robot Perception Simulation Framework](https://mlsanity.com/paper/2503.01074/) (2025)
- [Aquatic-GS: A Hybrid 3D Representation for Underwater Scenes](https://mlsanity.com/paper/2411.00239/) (2024)
- [PhotoReg: Photometrically Registering 3D Gaussian Splatting Models](https://mlsanity.com/paper/2410.05044/) (2024)
- [3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling](https://mlsanity.com/paper/2505.21238/) (2025)
- [AquaFuse: Waterbody Fusion for Physics Guided View Synthesis of Underwater Scenes](https://mlsanity.com/paper/2411.01119/) (2024)
- [Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models](https://mlsanity.com/paper/2503.06784/) (2025)
- [GraphSeg: Segmented 3D Representations via Graph Edge Addition and Contraction](https://mlsanity.com/paper/2504.03129/) (2025)
- [Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations](https://mlsanity.com/paper/2509.20703/) (2025)
- [Spatiotemporal Degradation-Aware 3D Gaussian Splatting for Realistic Underwater Scene Reconstruction](https://mlsanity.com/paper/2604.23551/) (2026)
- [Semantic-guided Gaussian Splatting for High-Fidelity Underwater Scene Reconstruction](https://mlsanity.com/paper/2509.00800/) (2025)
- [Swimm3R: Splatting with Medium-aware SfM for Underwater 3D Reconstruction](https://mlsanity.com/paper/2608.00950/) (2026)
- [Efficient Construction of Implicit Surface Models From a Single Image for Motion Generation](https://mlsanity.com/paper/2509.20681/) (2025)
- [OceanXL: Large-scale Underwater 3D Gaussian Splatting via Block Partitioning and Adaptive Pruning](https://mlsanity.com/paper/2609.29985/) (2026)
- [PUGS: Physics-Guided Uncertainty Modeling for Underwater Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2610.17936/) (2026)

## Abstract (arXiv)

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.