AVINet: adaptive variational iteration network for low light image enhancement

Abstract Images captured in dark environments often face challenges like low contrast and noise. Many enhancement methods based on variational models, set parameters artificially to improve contrast, which often does not adequately address real-world conditions. To address this, we propose an adapti...

Full description

Saved in:
Bibliographic Details
Main Authors: Tao Chen, Feng-Fei Jin, Jinqi Cui, Xiangyu Man, Dongmei Liu
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00167-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225821009477632
author Tao Chen
Feng-Fei Jin
Jinqi Cui
Xiangyu Man
Dongmei Liu
author_facet Tao Chen
Feng-Fei Jin
Jinqi Cui
Xiangyu Man
Dongmei Liu
author_sort Tao Chen
collection DOAJ
description Abstract Images captured in dark environments often face challenges like low contrast and noise. Many enhancement methods based on variational models, set parameters artificially to improve contrast, which often does not adequately address real-world conditions. To address this, we propose an adaptive variational model and establish an Adaptive Variational Iteration Network (AVINet). By designing a Parameter Extraction Module, we can adaptively learn the image contrast adjustment parameters within the model. Then, to prevent uneven image brightness, we introduce a smoothness term. We have mathematically proven the existence and uniqueness of the solution of this variational model, and then solve it using the Bregman iteration method. In the Denoising Module, we employ a denoising diffusion probability model to eliminate the noise in the image. Comparative experiments conducted on various datasets demonstrate that that our method achieves better results in restoring illumination and detail compared to other advanced methods.
format Article
id doaj-art-1bfc99dc25b64d95ba04aac8bf1e5020
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-1bfc99dc25b64d95ba04aac8bf1e50202025-08-24T11:53:48ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-08-0137711610.1007/s44443-025-00167-3AVINet: adaptive variational iteration network for low light image enhancementTao Chen0Feng-Fei Jin1Jinqi Cui2Xiangyu Man3Dongmei Liu4Shandong Normal UniversityShandong Normal UniversityShandong Normal UniversityShandong Normal UniversityShandong Normal UniversityAbstract Images captured in dark environments often face challenges like low contrast and noise. Many enhancement methods based on variational models, set parameters artificially to improve contrast, which often does not adequately address real-world conditions. To address this, we propose an adaptive variational model and establish an Adaptive Variational Iteration Network (AVINet). By designing a Parameter Extraction Module, we can adaptively learn the image contrast adjustment parameters within the model. Then, to prevent uneven image brightness, we introduce a smoothness term. We have mathematically proven the existence and uniqueness of the solution of this variational model, and then solve it using the Bregman iteration method. In the Denoising Module, we employ a denoising diffusion probability model to eliminate the noise in the image. Comparative experiments conducted on various datasets demonstrate that that our method achieves better results in restoring illumination and detail compared to other advanced methods.https://doi.org/10.1007/s44443-025-00167-3Low light image enhancementVariational modelDenoising diffusion probability model
spellingShingle Tao Chen
Feng-Fei Jin
Jinqi Cui
Xiangyu Man
Dongmei Liu
AVINet: adaptive variational iteration network for low light image enhancement
Journal of King Saud University: Computer and Information Sciences
Low light image enhancement
Variational model
Denoising diffusion probability model
title AVINet: adaptive variational iteration network for low light image enhancement
title_full AVINet: adaptive variational iteration network for low light image enhancement
title_fullStr AVINet: adaptive variational iteration network for low light image enhancement
title_full_unstemmed AVINet: adaptive variational iteration network for low light image enhancement
title_short AVINet: adaptive variational iteration network for low light image enhancement
title_sort avinet adaptive variational iteration network for low light image enhancement
topic Low light image enhancement
Variational model
Denoising diffusion probability model
url https://doi.org/10.1007/s44443-025-00167-3
work_keys_str_mv AT taochen avinetadaptivevariationaliterationnetworkforlowlightimageenhancement
AT fengfeijin avinetadaptivevariationaliterationnetworkforlowlightimageenhancement
AT jinqicui avinetadaptivevariationaliterationnetworkforlowlightimageenhancement
AT xiangyuman avinetadaptivevariationaliterationnetworkforlowlightimageenhancement
AT dongmeiliu avinetadaptivevariationaliterationnetworkforlowlightimageenhancement