A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

TL;DR

This paper introduces a novel deep learning pipeline combining CNNs and GANs, capable of learning from both paired and unpaired datasets to enhance low light images effectively.

Contribution

A new deep learning pipeline that leverages both paired and unpaired datasets for low light image enhancement using CNNs and GANs.

Findings

Improved low light image quality through the pipeline.

Effective use of cycle consistency and patched discriminator.

Analysis of component contributions to performance.

Abstract

Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.