# WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images

arXiv: https://arxiv.org/abs/1702.07392 · HTML: https://mlsanity.com/paper/1702.07392/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2017.

## Built on by (most cited first, 30 of 112)

- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [Uncertainty Inspired Underwater Image Enhancement](https://mlsanity.com/paper/2207.09689/) (2022)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [Shallow-UWnet : Compressed Model for Underwater Image Enhancement](https://mlsanity.com/paper/2101.02073/) (2021)
- [UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space](https://mlsanity.com/paper/2103.07138/) (2021)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy](https://mlsanity.com/paper/2309.03445/) (2023)
- [WaterNeRF: Neural Radiance Fields for Underwater Scenes](https://mlsanity.com/paper/2209.13091/) (2022)
- [SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images](https://mlsanity.com/paper/2302.08269/) (2023)
- [Underwater Light Field Retention : Neural Rendering for Underwater Imaging](https://mlsanity.com/paper/2203.11006/) (2022)
- [Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery](https://mlsanity.com/paper/2304.03384/) (2023)
- [UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement](https://mlsanity.com/paper/2404.14542/) (2024)
- [Low-Light Image and Video Enhancement: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2212.10772/) (2022)
- [Underwater Image Restoration Through a Prior Guided Hybrid Sense Approach and Extensive Benchmark Analysis](https://mlsanity.com/paper/2501.02701/) (2025)
- [A Wavelet-based Dual-stream Network for Underwater Image Enhancement](https://mlsanity.com/paper/2202.08758/) (2022)
- [Exploring the Underwater World Segmentation without Extra Training](https://mlsanity.com/paper/2511.07923/) (2025)
- [OysterNet: Enhanced Oyster Detection Using Simulation](https://mlsanity.com/paper/2209.08176/) (2022)
- [Underwater Image Enhancement via Learning Water Type Desensitized Representations](https://mlsanity.com/paper/2102.00676/) (2021)
- [Domain Adaptation for Underwater Image Enhancement via Content and Style Separation](https://mlsanity.com/paper/2202.08537/) (2022)
- [Towards More Efficient EfficientDets and Low-Light Real-Time Marine Debris Detection](https://mlsanity.com/paper/2203.07155/) (2022)
- [Is Underwater Image Enhancement All Object Detectors Need?](https://mlsanity.com/paper/2311.18814/) (2023)
- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration](https://mlsanity.com/paper/2107.02660/) (2021)
- [AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach](https://mlsanity.com/paper/2112.04974/) (2021)
- [DeepSeeColor: Realtime Adaptive Color Correction for Autonomous Underwater Vehicles via Deep Learning Methods](https://mlsanity.com/paper/2303.04025/) (2023)
- [MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility](https://mlsanity.com/paper/2312.15633/) (2023)

## Abstract (arXiv)

This paper reports on WaterGAN, a generative adversarial network (GAN) for generating realistic underwater images from in-air image and depth pairings in an unsupervised pipeline used for color correction of monocular underwater images. Cameras onboard autonomous and remotely operated vehicles can capture high resolution images to map the seafloor, however, underwater image formation is subject to the complex process of light propagation through the water column. The raw images retrieved are characteristically different than images taken in air due to effects such as absorption and scattering, which cause attenuation of light at different rates for different wavelengths. While this physical process is well described theoretically, the model depends on many parameters intrinsic to the water column as well as the objects in the scene. These factors make recovery of these parameters difficult without simplifying assumptions or field calibration, hence, restoration of underwater images is a non-trivial problem. Deep learning has demonstrated great success in modeling complex nonlinear systems but requires a large amount of training data, which is difficult to compile in deep sea environments. Using WaterGAN, we generate a large training dataset of paired imagery, both raw underwater and true color in-air, as well as depth data. This data serves as input to a novel end-to-end network for color correction of monocular underwater images. Due to the depth-dependent water column effects inherent to underwater environments, we show that our end-to-end network implicitly learns a coarse depth estimate of the underwater scene from monocular underwater images. Our proposed pipeline is validated with testing on real data collected from both a pure water tank and from underwater surveys in field testing. Source code is made publicly available with sample datasets and pretrained models.