# A deep learning approach for marine snow synthesis and removal

arXiv: https://arxiv.org/abs/2311.15584 · HTML: https://mlsanity.com/paper/2311.15584/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 75 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Builds on (most cited first, 13 of 13)

- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [Diving Deeper into Underwater Image Enhancement: A Survey](https://mlsanity.com/paper/1907.07863/) (2019)
- [All-In-One Underwater Image Enhancement using Domain-Adversarial Learning](https://mlsanity.com/paper/1905.13342/) (2019)
- [Deep Underwater Image Enhancement](https://mlsanity.com/paper/1807.03528/) (2018)
- [SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots](https://mlsanity.com/paper/2011.06252/) (2020)
- [UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing](https://mlsanity.com/paper/1912.10269/) (2019)
- [Underwater Image Super-Resolution using Deep Residual Multipliers](https://mlsanity.com/paper/1909.09437/) (2019)
- [Marine Snow Removal Benchmarking Dataset](https://mlsanity.com/paper/2103.14249/) (2021)
- [The Next Best Underwater View](https://mlsanity.com/paper/1512.01789/) (2015)

## Built on by (most cited first, 2 of 2)

- [Marine Snow Removal Using Internally Generated Pseudo Ground Truth](https://mlsanity.com/paper/2504.19289/) (2025)
- [Robust Image Processing Techniques for Construction Environment Monitoring Using Underwater Robots](https://mlsanity.com/paper/2607.01915/) (2026)

## Abstract (arXiv)

Marine snow, the floating particles in underwater images, severely degrades the visibility and performance of human and machine vision systems. This paper proposes a novel method to reduce the marine snow interference using deep learning techniques. We first synthesize realistic marine snow samples by training a Generative Adversarial Network (GAN) model and combine them with natural underwater images to create a paired dataset. We then train a U-Net model to perform marine snow removal as an image to image translation task. Our experiments show that the U-Net model can effectively remove both synthetic and natural marine snow with high accuracy, outperforming state-of-the-art methods such as the Median filter and its adaptive variant. We also demonstrate the robustness of our method by testing it on the MSRB dataset, which contains synthetic artifacts that our model has not seen during training. Our method is a practical and efficient solution for enhancing underwater images affected by marine snow.