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

TL;DR

This paper introduces a self-supervised deep learning method for underwater image enhancement that effectively improves image quality without needing paired datasets, using an attention mechanism to reduce high-intensity artifacts.

Contribution

It proposes a novel self-supervised approach with an attention module for underwater image enhancement, eliminating the need for ground-truth data and addressing high-intensity region issues.

Findings

Effective color preservation and contrast enhancement

Reduces color cast and high-intensity artifacts

Trained solely on real underwater images

Abstract

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 \textit{misleads} 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.