# Underwater enhancement based on a self-learning strategy and attention mechanism for high-intensity regions

arXiv: https://arxiv.org/abs/2208.03319 · HTML: https://mlsanity.com/paper/2208.03319/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 4 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions](https://mlsanity.com/paper/1901.05320/) (2019)
- [UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space](https://mlsanity.com/paper/2103.07138/) (2021)
- [Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map](https://mlsanity.com/paper/1906.08673/) (2019)
- [Learning Dynamics of Linear Denoising Autoencoders](https://mlsanity.com/paper/1806.05413/) (2018)
- [An Experimental-based Review of Image Enhancement and Image Restoration Methods for Underwater Imaging](https://mlsanity.com/paper/1907.03246/) (2019)
- [Enhancing Underwater Image via Adaptive Color and Contrast Enhancement, and Denoising](https://mlsanity.com/paper/2104.01073/) (2021)
- [Underwater Color Restoration Using U-Net Denoising Autoencoder](https://mlsanity.com/paper/1905.09000/) (2019)

## Built on by (most cited first, 4 of 4)

- [SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images](https://mlsanity.com/paper/2302.04233/) (2023)
- [UDBE: Unsupervised Diffusion-based Brightness Enhancement in Underwater Images](https://mlsanity.com/paper/2501.16211/) (2025)
- [Sonar Image Datasets: A Comprehensive Survey of Resources, Challenges, and Applications](https://mlsanity.com/paper/2510.03353/) (2025)
- [AquaFeat: A Features-Based Image Enhancement Model for Underwater Object Detection](https://mlsanity.com/paper/2508.12343/) (2025)

## Abstract (arXiv)

Images acquired during underwater activities suffer from environmental properties of the water, such as turbidity and light attenuation. These phenomena cause color distortion, blurring, and contrast reduction. In addition, irregular ambient light distribution causes color channel unbalance and regions with high-intensity pixels. Recent works related to underwater image enhancement, and based on deep learning approaches, tackle the lack of paired datasets generating synthetic ground-truth. In this paper, we present a self-supervised learning methodology for underwater image enhancement based on deep learning that requires no paired datasets. The proposed method estimates the degradation present in underwater images. Besides, an autoencoder reconstructs this image, and its output image is degraded using the estimated degradation information. Therefore, the strategy replaces the output image with the degraded version in the loss function during the training phase. This procedure textitmisleads the neural network that learns to compensate the additional degradation. As a result, the reconstructed image is an enhanced version of the input image. Also, the algorithm presents an attention module to reduce high-intensity areas generated in enhanced images by color channel unbalances and outlier regions. Furthermore, the proposed methodology requires no ground-truth. Besides, only real underwater images were used to train the neural network, and the results indicate the effectiveness of the method in terms of color preservation, color cast reduction, and contrast improvement.