More than Lightening: A Self-supervised Low-light Image Enhancement Method Capable for Multiple Degradations

doi:10.1109/JAS.2024.124263

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	More than Lightening: A Self-supervised Low-light Image Enhancement Method Capable for Multiple Degradations
	Han Xu; Jiayi Ma; Yixuan Yuan; Hao Zhang; Xin Tian; Xiaojie Guo
刊名	IEEE/CAA Journal of Automatica Sinica
	2024
卷号	11 期号:3 页码:622-637
关键词	Color correction low-light image enhancement self-supervised learning
ISSN号	2329-9266
DOI	10.1109/JAS.2024.124263
英文摘要	Low-light images suffer from low quality due to poor lighting conditions, noise pollution, and improper settings of cameras. To enhance low-light images, most existing methods rely on normal-light images for guidance when imaging and shooting conditions make the collection of suitable normal-light images difficult. In contrast, a self-supervised method breaks free from the reliance on normal-light data, resulting in more convenience and better generalization. Existing self-supervised methods primarily focus on illumination adjustment and design pixel-based adjustment methods, resulting in remnants of other degradations, uneven brightness and artifacts. In response, this paper proposes a self-supervised enhancement method, termed as SLIE. It can handle multiple degradations including illumination attenuation, noise pollution, and color shift, all in a selfsupervised manner. Illumination attenuation is estimated based on physical principles and local neighborhood information. The removal and correction of noise and color shift removal are solely realized with noisy images and images with color shifts. Finally, the comprehensive and fully self-supervised approach can achieve better adaptability and generalization. It is applicable to various low light conditions, and can reproduce the original color of scenes in natural light. Extensive experiments conducted on four publicly available datasets demonstrate the superiority of SLIE to thirteen state-of-the-art methods. Moreover, SLIE strikes a balance between parameters, efficiency, and performance, boasting fewer parameters than most existing learning-based methods.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54595]
专题	自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Han Xu,Jiayi Ma,Yixuan Yuan,et al. More than Lightening: A Self-supervised Low-light Image Enhancement Method Capable for Multiple Degradations[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(3):622-637.
APA	Han Xu,Jiayi Ma,Yixuan Yuan,Hao Zhang,Xin Tian,&Xiaojie Guo.(2024).More than Lightening: A Self-supervised Low-light Image Enhancement Method Capable for Multiple Degradations.IEEE/CAA Journal of Automatica Sinica,11(3),622-637.
MLA	Han Xu,et al."More than Lightening: A Self-supervised Low-light Image Enhancement Method Capable for Multiple Degradations".IEEE/CAA Journal of Automatica Sinica 11.3(2024):622-637.