Half Wavelet Attention on M-Net+ for Low-Light Image Enhancement

TL;DR

This paper introduces HWMNet, a novel deep neural network that employs half wavelet attention within an improved hierarchical M-Net+ architecture to enhance low-light images, achieving superior results in both quantitative metrics and visual quality.

Contribution

The paper proposes a new low-light image enhancement network, HWMNet, integrating half wavelet attention into M-Net+ to improve feature extraction and enhancement performance.

Findings

HWMNet outperforms existing methods on two datasets.

The use of wavelet attention enriches feature representation.

HWMNet achieves better visual quality and quantitative scores.

Abstract

Low-Light Image Enhancement is a computer vision task which intensifies the dark images to appropriate brightness. It can also be seen as an ill-posed problem in image restoration domain. With the success of deep neural networks, the convolutional neural networks surpass the traditional algorithm-based methods and become the mainstream in the computer vision area. To advance the performance of enhancement algorithms, we propose an image enhancement network (HWMNet) based on an improved hierarchical model: M-Net+. Specifically, we use a half wavelet attention block on M-Net+ to enrich the features from wavelet domain. Furthermore, our HWMNet has competitive performance results on two image enhancement datasets in terms of quantitative metrics and visual quality. The source code and pretrained model are available at https://github.com/FanChiMao/HWMNet.