Unsupervised Low-Light Image Enhancement via Feature Smoothing and Curve Regression
- 5 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 2475-2479
Abstract
Various methods have been discussed in the field of Low-light Image Enhancement (LIE), however the inability to effectively restrain noise still led to unsupervised LIE remaining a challenge. Traditional supervised LIE methods had the advantage of suppressing noise, but they suffer from generalization problems since the pairing of low-light and normal-light images are always required in the process. To this end, this work introduces an unsupervised LIE enhancement method that eliminates the need for paired images and effectively suppresses noise. The method utilizes the Retinex image decomposition technique to split the image into illumination and reflection components and processes the features of each part separately. In addition, we designed two deep learning architectures, lighting net (LINet) and denoising net (DNNet), to brighten the illumination component and denoise the reflection component respectively. We validate our method on two well-known open datasets and compared it with the state-of-the-art approaches. The experiments show that that the proposed method performs well in dimly lit scenes and visual verification, all quantitative metrics have at least 8% improvement on the best performing validation set.Keywords
Funding Information
- National Key Research & Development Program of China (2018AAA0102902)
- Guangxi Key Research and Development Program (AB24010164, AB21220038, AB23026048)
This publication has 16 references indexed in Scilit:
- Toward Fast, Flexible, and Robust Low-Light Image Enhancement2022
- SNR-Aware Low-light Image Enhancement2022
- Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement2021
- A Comparative Study on CNN based Low-light Image Enhancement2021
- Learning to Restore Low-Light Images via Decomposition-and-Enhancement2020
- From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement2020
- Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement2020
- Low-Light Image Enhancement Based on Joint Generative Adversarial Network and Image Quality Assessment2018
- GLADNet: Low-Light Enhancement Network with Global Awareness2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015