Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer

TL;DR

This paper introduces a weakly supervised color transfer method for underwater images that corrects color distortion without needing paired training data, improving visual quality and aiding vision tasks.

Contribution

It proposes a novel weakly supervised approach based on CycleGAN that relaxes data requirements and effectively corrects underwater image colors.

Findings

Produces visually pleasing color correction results

Outperforms state-of-the-art methods in experiments

Enhances performance of underwater vision tasks

Abstract

Underwater vision suffers from severe effects due to selective attenuation and scattering when light propagates through water. Such degradation not only affects the quality of underwater images but limits the ability of vision tasks. Different from existing methods which either ignore the wavelength dependency of the attenuation or assume a specific spectral profile, we tackle color distortion problem of underwater image from a new view. In this letter, we propose a weakly supervised color transfer method to correct color distortion, which relaxes the need of paired underwater images for training and allows for the underwater images unknown where were taken. Inspired by Cycle-Consistent Adversarial Networks, we design a multi-term loss function including adversarial loss, cycle consistency loss, and SSIM (Structural Similarity Index Measure) loss, which allows the content and structure of the corrected result the same as the input, but the color as if the image was taken without the water. Experiments on underwater images captured under diverse scenes show that our method produces visually pleasing results, even outperforms the art-of-the-state methods. Besides, our method can improve the performance of vision tasks.