Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines

Abstract The images in underground coal mines suffer from low contrast and poor visibility. While diffusion model-based approaches for low-light image enhancement have shown considerable promise, these methods are often characterized by high resource consumption, slow processing speeds, and a tenden...

Full description

Saved in:
Bibliographic Details
Main Authors: Yadong Li, Jun Tian, Yang Chen, Hongdong Wang, Hui Yan, Yang Peng, Tianjiao Wang
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-01966-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331456374996992
author Yadong Li
Jun Tian
Yang Chen
Hongdong Wang
Hui Yan
Yang Peng
Tianjiao Wang
author_facet Yadong Li
Jun Tian
Yang Chen
Hongdong Wang
Hui Yan
Yang Peng
Tianjiao Wang
author_sort Yadong Li
collection DOAJ
description Abstract The images in underground coal mines suffer from low contrast and poor visibility. While diffusion model-based approaches for low-light image enhancement have shown considerable promise, these methods are often characterized by high resource consumption, slow processing speeds, and a tendency towards instability. To address these challenges, this paper presents a diffusion model that integrates Retinex and Wavelet transform (RW-DM). This methodology harnesses the generative capabilities of diffusion models to produce visually appealing outcomes in the enhancement of low-light images. This approach decomposes low-light images into reflectance and illumination components, utilizing the advantages of wavelet transformation to significantly enhance processing speed and reduce computational resource consumption while preserving data integrity. Additionally, the study introduces a Multiple Residual Module (MRM) to preserve details in both the decomposing network (MR-Decompose) and the denoising network (MRU-Denoise). Extensive experiments on low-light images from coal mines demonstrate that RW-DM outperforms existing state-of-the-art methods qualitatively. Moreover, the application of the proposed method in pedestrian detection using underground coal mine images resulted in a 3.1% increase in $$\hbox {mAP}_{50}$$ mAP 50 . This improvement not only showcases the effectiveness of the proposed approach but also highlights its potential practical value.
format Article
id doaj-art-2925248ac43f4e2a87d2628997100aaf
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-2925248ac43f4e2a87d2628997100aaf2025-08-20T03:46:34ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-06-0111811710.1007/s40747-025-01966-xRw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal minesYadong Li0Jun Tian1Yang Chen2Hongdong Wang3Hui Yan4Yang Peng5Tianjiao Wang6School of Information and Control Engineering, China University of Mining and TechnologySchool of Information and Control Engineering, China University of Mining and TechnologySchool of Electrical Engineering, China University of Mining and TechnologySchool of Information and Control Engineering, China University of Mining and TechnologySchool of Intelligent Engineering, Jiangsu Vocational College of Information TechnologySchool of Low-Carbon Energy and Power Engineering, China University of Mining and TechnologySchool of Electrical Engineering and Automation, Jiangsu Normal UniversityAbstract The images in underground coal mines suffer from low contrast and poor visibility. While diffusion model-based approaches for low-light image enhancement have shown considerable promise, these methods are often characterized by high resource consumption, slow processing speeds, and a tendency towards instability. To address these challenges, this paper presents a diffusion model that integrates Retinex and Wavelet transform (RW-DM). This methodology harnesses the generative capabilities of diffusion models to produce visually appealing outcomes in the enhancement of low-light images. This approach decomposes low-light images into reflectance and illumination components, utilizing the advantages of wavelet transformation to significantly enhance processing speed and reduce computational resource consumption while preserving data integrity. Additionally, the study introduces a Multiple Residual Module (MRM) to preserve details in both the decomposing network (MR-Decompose) and the denoising network (MRU-Denoise). Extensive experiments on low-light images from coal mines demonstrate that RW-DM outperforms existing state-of-the-art methods qualitatively. Moreover, the application of the proposed method in pedestrian detection using underground coal mine images resulted in a 3.1% increase in $$\hbox {mAP}_{50}$$ mAP 50 . This improvement not only showcases the effectiveness of the proposed approach but also highlights its potential practical value.https://doi.org/10.1007/s40747-025-01966-xDeep learningLow-light image enhancementMulti-Scale feature extractionIntegration of Retinex and Wavelet transform
spellingShingle Yadong Li
Jun Tian
Yang Chen
Hongdong Wang
Hui Yan
Yang Peng
Tianjiao Wang
Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines
Complex & Intelligent Systems
Deep learning
Low-light image enhancement
Multi-Scale feature extraction
Integration of Retinex and Wavelet transform
title Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines
title_full Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines
title_fullStr Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines
title_full_unstemmed Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines
title_short Rw-Dm: Retinex and wavelet-based diffusion model for low-light image enhancement in underground coal mines
title_sort rw dm retinex and wavelet based diffusion model for low light image enhancement in underground coal mines
topic Deep learning
Low-light image enhancement
Multi-Scale feature extraction
Integration of Retinex and Wavelet transform
url https://doi.org/10.1007/s40747-025-01966-x
work_keys_str_mv AT yadongli rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines
AT juntian rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines
AT yangchen rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines
AT hongdongwang rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines
AT huiyan rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines
AT yangpeng rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines
AT tianjiaowang rwdmretinexandwaveletbaseddiffusionmodelforlowlightimageenhancementinundergroundcoalmines