# DGD-cGAN: A Dual Generator for Image Dewatering and Restoration

arXiv: https://arxiv.org/abs/2211.10026 · HTML: https://mlsanity.com/paper/2211.10026/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 73 references that are in the map.
- First posted on arXiv 18 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Revisiting Small Batch Training for Deep Neural Networks](https://mlsanity.com/paper/1804.07612/) (2018)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception](https://mlsanity.com/paper/2002.01155/) (2020)
- [UWGAN: Underwater GAN for Real-world Underwater Color Restoration and Dehazing](https://mlsanity.com/paper/1912.10269/) (2019)
- [Effects of Image Degradations to CNN-based Image Classification](https://mlsanity.com/paper/1810.05552/) (2018)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [Underwater Image Enhancement by Convolutional Spiking Neural Networks](https://mlsanity.com/paper/2503.20485/) (2025)
- [Image-Conditional Diffusion Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2407.05389/) (2024)
- [Underwater Image Enhancement via Dehazing and Color Restoration](https://mlsanity.com/paper/2409.09779/) (2024)
- [Enhancing Image Restoration through Learning Context-Rich and Detail-Accurate Features](https://mlsanity.com/paper/2504.10558/) (2025)
- [snnTrans-DHZ: A Lightweight Spiking Neural Network Architecture for Underwater Image Dehazing](https://mlsanity.com/paper/2504.11482/) (2025)

## Abstract (arXiv)

Underwater images are usually covered with a blue-greenish colour cast, making them distorted, blurry or low in contrast. This phenomenon occurs due to the light attenuation given by the scattering and absorption in the water column. In this paper, we present an image enhancement approach for dewatering which employs a conditional generative adversarial network (cGAN) with two generators. Our Dual Generator Dewatering cGAN (DGD-cGAN) removes the haze and colour cast induced by the water column and restores the true colours of underwater scenes whereby the effects of various attenuation and scattering phenomena that occur in underwater images are tackled by the two generators. The first generator takes at input the underwater image and predicts the dewatered scene, while the second generator learns the underwater image formation process by implementing a custom loss function based upon the transmission and the veiling light components of the image formation model. Our experiments show that DGD-cGAN consistently delivers a margin of improvement as compared with the state-of-the-art methods on several widely available datasets.