Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework

Images captured under low-light conditions often suffer from serious degradation due to insufficient light, which adversely impacts subsequent computer vision tasks. Retinex-based methods have demonstrated strong potential in low-light image enhancement. However, existing approaches often directly d...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenping Zhao, Wenlong Yue, Yingjun Wang, Jianping Wang, Shousheng Luo, Huazhu Chen, Yan Wang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/24/4025
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241567557681152
author Chenping Zhao
Wenlong Yue
Yingjun Wang
Jianping Wang
Shousheng Luo
Huazhu Chen
Yan Wang
author_facet Chenping Zhao
Wenlong Yue
Yingjun Wang
Jianping Wang
Shousheng Luo
Huazhu Chen
Yan Wang
author_sort Chenping Zhao
collection DOAJ
description Images captured under low-light conditions often suffer from serious degradation due to insufficient light, which adversely impacts subsequent computer vision tasks. Retinex-based methods have demonstrated strong potential in low-light image enhancement. However, existing approaches often directly design prior regularization functions for either illumination or reflectance components, which may unintentionally introduce noise. To address these limitations, this paper presents an enhancement method by integrating a Plug-and-Play strategy into an extended decomposition model. The proposed model consists of three main components: an extended decomposition term, an iterative reweighting regularization function for the illumination component, and a Plug-and-Play refinement term applied to the reflectance component. The extended decomposition enables a more precise representation of image components, while the iterative reweighting mechanism allows for gentle smoothing near edges and brighter areas while applying more pronounced smoothing in darker regions. Additionally, the Plug-and-Play framework incorporates off-the-shelf image denoising filters to effectively suppress noise and preserve useful image details. Extensive experiments on several datasets confirm that the proposed method consistently outperforms existing techniques.
format Article
id doaj-art-bc8488a69ffe4b1b846b2a048e30db51
institution OA Journals
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-bc8488a69ffe4b1b846b2a048e30db512025-08-20T02:00:34ZengMDPI AGMathematics2227-73902024-12-011224402510.3390/math12244025Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play FrameworkChenping Zhao0Wenlong Yue1Yingjun Wang2Jianping Wang3Shousheng Luo4Huazhu Chen5Yan Wang6Postdoctoral Research Station of Physics, Henan Normal University, Xinxiang 453007, ChinaSchool of Mathematical Science, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Information Engineering, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang 453003, ChinaCollege of Mathematical Medicine, Zhejiang Normal University, Jinhua 321000, ChinaSchool of Mathematics and Information Sciences, Zhongyuan University of Technology, Zhengzhou 451191, ChinaSchool of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang 453003, ChinaImages captured under low-light conditions often suffer from serious degradation due to insufficient light, which adversely impacts subsequent computer vision tasks. Retinex-based methods have demonstrated strong potential in low-light image enhancement. However, existing approaches often directly design prior regularization functions for either illumination or reflectance components, which may unintentionally introduce noise. To address these limitations, this paper presents an enhancement method by integrating a Plug-and-Play strategy into an extended decomposition model. The proposed model consists of three main components: an extended decomposition term, an iterative reweighting regularization function for the illumination component, and a Plug-and-Play refinement term applied to the reflectance component. The extended decomposition enables a more precise representation of image components, while the iterative reweighting mechanism allows for gentle smoothing near edges and brighter areas while applying more pronounced smoothing in darker regions. Additionally, the Plug-and-Play framework incorporates off-the-shelf image denoising filters to effectively suppress noise and preserve useful image details. Extensive experiments on several datasets confirm that the proposed method consistently outperforms existing techniques.https://www.mdpi.com/2227-7390/12/24/4025low-light imagedecomposition modeliterative reweighting regularizationPlug-and-Play
spellingShingle Chenping Zhao
Wenlong Yue
Yingjun Wang
Jianping Wang
Shousheng Luo
Huazhu Chen
Yan Wang
Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework
Mathematics
low-light image
decomposition model
iterative reweighting regularization
Plug-and-Play
title Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework
title_full Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework
title_fullStr Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework
title_full_unstemmed Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework
title_short Low-Light Image Enhancement Integrating Retinex-Inspired Extended Decomposition with a Plug-and-Play Framework
title_sort low light image enhancement integrating retinex inspired extended decomposition with a plug and play framework
topic low-light image
decomposition model
iterative reweighting regularization
Plug-and-Play
url https://www.mdpi.com/2227-7390/12/24/4025
work_keys_str_mv AT chenpingzhao lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework
AT wenlongyue lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework
AT yingjunwang lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework
AT jianpingwang lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework
AT shoushengluo lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework
AT huazhuchen lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework
AT yanwang lowlightimageenhancementintegratingretinexinspiredextendeddecompositionwithaplugandplayframework