U-shape Transformer for Underwater Image Enhancement

TL;DR

This paper introduces a large-scale underwater image dataset and a novel U-shape Transformer network with specialized modules and a new loss function, achieving state-of-the-art results in underwater image enhancement.

Contribution

The work presents the first application of a Transformer model to underwater image enhancement, along with a new dataset and a specialized loss function for improved performance.

Findings

Achieved over 2dB improvement in image quality metrics

Constructed a dataset with 5004 image pairs for training and evaluation

Demonstrated superior performance over existing methods

Abstract

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement. In this work, we constructed a large-scale underwater image (LSUI) dataset including 5004 image pairs, and reported an U-shape Transformer network where the transformer model is for the first time introduced to the UIE task. The U-shape Transformer is integrated with a channel-wise multi-scale feature fusion transformer (CMSFFT) module and a spatial-wise global feature modeling transformer (SGFMT) module, which reinforce the network's attention to the color channels and space areas with more serious attenuation. Meanwhile, in order to further improve the contrast and saturation, a novel loss function combining RGB, LAB and LCH color spaces is designed following the human vision principle. The extensive experiments on available datasets validate the state-of-the-art performance of the reported technique with more than 2dB superiority.