MSR-net:Low-light Image Enhancement Using Deep Convolutional Network

TL;DR

This paper introduces MSR-net, a deep convolutional neural network that enhances low-light images by learning an end-to-end mapping, outperforming existing methods in both qualitative and quantitative evaluations.

Contribution

The paper presents a novel CNN-based model for low-light image enhancement inspired by Retinex theory, with parameters learned through back-propagation, unlike traditional approaches.

Findings

MSR-net outperforms state-of-the-art methods in quality metrics.

The model effectively enhances contrast and brightness in challenging low-light images.

End-to-end learning simplifies the enhancement process.

Abstract

Images captured in low-light conditions usually suffer from very low contrast, which increases the difficulty of subsequent computer vision tasks in a great extent. In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed. Firstly, we show that multi-scale Retinex is equivalent to a feedforward convolutional neural network with different Gaussian convolution kernels. Motivated by this fact, we consider a Convolutional Neural Network(MSR-net) that directly learns an end-to-end mapping between dark and bright images. Different fundamentally from existing approaches, low-light image enhancement in this paper is regarded as a machine learning problem. In this model, most of the parameters are optimized by back-propagation, while the parameters of traditional models depend on the artificial setting. Experiments on a number of challenging images reveal the advantages of our method in comparison with other state-of-the-art methods from the qualitative and quantitative perspective.