Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network

TL;DR

This paper introduces a novel low-light image enhancement method combining Retinex theory with a GAN, effectively improving image clarity in extremely poor illumination conditions through decomposition and enhancement stages.

Contribution

The work presents a new GAN-based framework integrated with Retinex theory for low-light image enhancement, addressing limitations of previous methods in extremely dark areas.

Findings

Achieved satisfactory enhancement results on CSID datasets.

Outperformed existing methods in clarity and noise reduction.

Proved effectiveness of combining Retinex with GAN for low-light images.

Abstract

Low-light image enhancement is generally regarded as a challenging task in image processing, especially for the complex visual tasks at night or weakly illuminated. In order to reduce the blurs or noises on the low-light images, a large number of papers have contributed to applying different technologies. Regretfully, most of them had served little purposes in coping with the extremely poor illumination parts of images or test in practice. In this work, the authors propose a novel approach for processing low-light images based on the Retinex theory and generative adversarial network (GAN), which is composed of the decomposition part for splitting the image into illumination image and reflected image, and the enhancement part for generating high-quality image. Such a discriminative network is expected to make the generated image clearer. Couples of experiments have been implemented under the circumstance of different lighting strength on the basis of Converted See-In-the-Dark (CSID) datasets, and the satisfactory results have been achieved with exceeding expectation that much encourages the authors. In a word, the proposed GAN-based network and employed Retinex theory in this work have proven to be effective in dealing with the low-light image enhancement problems, which will benefit the image processing with no doubt.