Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement

TL;DR

This paper introduces CIGAN, a novel unsupervised GAN framework that enhances low-light images by better transferring illumination and suppressing noise through cycle-interactive processes and feature manipulation.

Contribution

The paper proposes a cycle-interactive GAN with feature transfer and randomized perturbation modules for improved unsupervised low-light image enhancement.

Findings

Outperforms existing methods in noise suppression and illumination transfer.

Effectively synthesizes diverse realistic low-light images.

Modules significantly improve enhancement quality.

Abstract

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement, the remaining noise suppression issue due to the lacking of supervision of detailed signal largely impedes the wide deployment of these methods in real-world applications. Herein, we propose a novel Cycle-Interactive Generative Adversarial Network (CIGAN) for unsupervised low-light image enhancement, which is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g., suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN (eGAN) into the generator of degradation GAN (dGAN). With the learned information of real low-light images, dGAN can synthesize more realistic diverse illumination and contrast in low-light images. Moreover, the feature randomized perturbation module in dGAN learns to increase the feature randomness to produce diverse feature distributions, persuading the synthesized low-light images to contain realistic noise. Extensive experiments demonstrate both the superiority of the proposed method and the effectiveness of each module in CIGAN.