计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (10): 168-175.doi: 10.11896/jsjkx.240800057

• 计算机图形学&多媒体 • 上一篇    下一篇

基于Retinex理论的低照度图像自适应增强算法

郑涤尘1, 何继开1, 刘艺2, 高帆1, 张登银2   

  1. 1 南京邮电大学通信与信息工程学院 南京 210003
    2 南京邮电大学物联网学院 南京 210003
  • 收稿日期:2024-08-09 修回日期:2024-10-13 出版日期:2025-10-15 发布日期:2025-10-14
  • 通讯作者: 张登银(zhangdy@njupt.edu.cn)
  • 作者简介:(1425234019@qq.com)
  • 基金资助:
    国家自然科学基金(61872423)

Low Light Image Adaptive Enhancement Algorithm Based on Retinex Theory

ZHENG Dichen1, HE Jikai1, LIU Yi2, GAO Fan1, ZHANG Dengyin2   

  1. 1 School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
    2 School of Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Received:2024-08-09 Revised:2024-10-13 Online:2025-10-15 Published:2025-10-14
  • About author:ZHENG Dichen,born in 2000,post-graduate.His main research interests include image processing and computer vision.
    ZHANG Dengyin,born in 1964,Ph.D,researcher,Ph.D supervisor.His main research interests include signal and information processing and information security.
  • Supported by:
    National Natural Science Foundation of China(61872423).

PDF (PC)

2

摘要： 现实环境中图像通常在次优照明条件下拍摄,导致亮度不足、观感较差。现有低照度图像增强方法往往结构复杂,侧重于改善暗光区域的可视度,但可能过度增强图像的明亮区域,放大隐藏的噪声。多数基于Retinex理论的方法存在噪点过多、细节损失和颜色失真等问题,影响增强结果的视觉质量。为了解决该问题,提出了一种基于Retinex理论的低照度图像自适应增强算法,旨在有效提升图像亮度的同时真实、自然地还原图像。首先,低照度图像经过投影模块去除不适合Retinex理论分解的噪声;其次,分解网络将图像分解为照度分量和反射分量;最后,照度分量经过自适应迭代曲线进行调整,与反射分量相乘得到增强图像。实验结果表明,相比于其他主流算法,所提算法在客观评价指标特别是PSNR和SSIM上优势明显:在LOL数据集上分别达到19.98 dB和0.76,较次优算法提高4.9%和4.1%;在LSRW数据集上分别达到18.94 dB和0.58,较次优算法提高1.5%和7.4%。在有参考数据集和无参考数据集上,所提算法得到的增强图像的亮度均有显著提升,色彩真实自然,主观视觉效果更好。

关键词: 图像增强, 低照度, Retinex, 迭代增强, 深度学习

Abstract: Images in real-world environments are often shot under sub-optimal lighting conditions,resulting in insufficient brightness and poor visual experience.Existing low-light image enhancement methods are often complex in structure and focus on improving the visibility of dark areas,but may over-enhance the bright areas of the image and amplify hidden noise.Most methods based on Retinex theory have problems such as excessive noise,loss of details and color distortion,which affect the visual quality of the enhancement results.In order to solve this problem,this paper proposes a low-light image adaptive enhancement algorithm based on Retinex theory,which aims to effectively improve the brightness of the image while restoring the image truly and naturally.Firstly,the low-light image is passed through the projection module to remove noise that is not suitable for Retinex decomposition.Secondly,the decomposition network decomposes the image into an illumination component and a reflection component.Finally,the illumination component is adjusted through an adaptive iterative curve and multiplied with the reflection component to obtain an enhanced image.Experimental results show that compared with other mainstream algorithms,the proposed algorithm has obvious advantages in objective evaluation indicators,especially PSNR and SSIM:tests on the LOL dataset show that PSNR and SSIM reach 19.98 dB and 0.76,respectively,which are 4.9% and 4.1% higher than the suboptimal algorithm;tests on the LSRW dataset show that PSNR and SSIM reach 18.94 dB and 0.58,respectively,which are 1.5% and 7.4% higher than the suboptimal algorithm.On both of the referenced dataset and the non-reference dataset,the brightness of the enhanced image obtained by the proposed algorithm is significantly improved,the colors are more realistic and natural,and the subjective visual effect is better.

Key words: Image enhancement,Low-light,Retinex,Iterative enhancement,Deep learning

中图分类号: 

  • TP391
[1]WU X Q,ZHOU W J,ZUO C L,et al.Salient object detection method based on multi-scale visual perception feature fusion[J].Computer Science,2024,51(5):143-150.
[2]LIU Y T,LI P,SUN Y Y,et al.Image recognition with deep dynamic joint adaptation networks[J].Computer Science,2021,48(6):131-137.
[3]ZHANG F C,ZHONG G Q,MAO Y X.Neural architecturesearch for light-weight medical image segmentation network[J].Computer Science,2022,49(10):183-190.
[4]IBRAHIM H,KONG N S P.Brightness preserving dynamic histogram equalization for image contrast enhancement [J].IEEE Transactions on Consumer Electronics,2007,53(4):1752-1758.
[5]JOHN J M.Lightness and retinex theory [J].Journal of the Optical Society of America,1970,61(1):1-11.
[6]LORE K G,AKINTAYO A,SARKAR S.LLNet:a deep autoencoder approach to natural low-light image enhancement [J].Pattern Recognition,2017,61:650-662.
[7]WEI C,WANG W,YANG W,et al.Deep retinex decomposition for low-light enhancement [J].arXiv:1808.04560,2018.
[8]ZHANG Y,ZHANG J,GUO X.Kindling the darkness:A practical low-light image enhancer [C]//Proceedings of the 27th ACM International Conference on Multimedia.2019:1632-1640.
[9]ZHANG Y,GUO X,MA J,et al.Beyond brightening low-light images [J].International Journal of Computer Vision,2021,129(4):1013-1037.
[10]LIU R,MA L,ZHANG J,et al.Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:10561-10570.
[11]ZHAO Z,XIONG B,WANG L,et al.RetinexDIP:A UnifiedDeep Framework for Low-Light Image Enhancement [J].IEEE Transactions on Circuits and Systems for Video Technology,2022,32(3):1076-1088.
[12]HAI J,XUAN Z,YANG R,et al.R2RNet:Low-light image enhancement via Real-low to Real-normal Network [J].Journal of Visual Communication and Image Representation,2023,90:1037-1048.
[13]ZHANG L,ZHANG L,LIU X,et al.Zero-shot restoration of back-lit images using deep internal learning [C]//Proceedings of the 27th ACM International Conference on Multimedia.2019:1623-1631.
[14]GUO C,LI C,GUO J,et al.Zero-reference deep curve estimation for low-light image enhancement [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:1780-1789.
[15]ZHU A,ZHANG L,SHEN Y,et al.Zero-Shot Restoration of Underexposed Images via Robust Retinex Decomposition [C]//Proceedings of the IEEE/CVF International Conference on Multimedia and Expo.2020:1-6.
[16]ZHENG S,GUPTA G.Semantic-guided zero-shot learning forlowlight image/video enhancement [C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2022:581-590.
[17]WEN J,WU C,ZHANG T,et al.Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement [J].ar-Xiv:2308.08197,2023.
[18]JIANG Y,GONG X,LIU D,et al.Enlightengan:Deep light enhancement without paired supervision [J].IEEE Transactions on Image Processing,2021,30:2340-2349.
[19]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional networks for biomedical image segmentation [C]//Proceedings of the Medical Image Computing and Computer-Assisted Intervention.2015:234-241.
[20]MA L,MA T,LIU R,et al.Toward fast,flexible,and robustlow-light image enhancement [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5637-5646.
[21]CUI Z,LI K,GU L,et al.You Only Need 90K Parameters toAdapt Light:a Light Weight Transformer for Image Enhancement and Exposure Correction [J].arXiv:2205.14871,2022.
[22]SHAKIBANIA H,RAOUFI S,KHOTANLOU H.CDAN:Convolutional Dense Attention-guided Network for Low-light Image Enhancement [J].arXiv:2308.12902,2023.
[23]JIANG H,LUO A,LIU X H,et al.LightenDiffusion:Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models [J].arXiv:2407.08939,2024.
[24]CHOBOLA T,LIU Y,ZHANG H,et al.Fast Context-BasedLow-Light Image Enhancement via Neural Implicit Representations [J].arXiv:2407.12511,2024.
[25]CHEN Y,ZHU G,WANG X,et al.FMR-Net:a fast multi-scale residual network for low-light image enhancement [J].Multimedia Systems,2024,30(2):73.
[26]SHI Y F,ZHAO B T.Low-light Image Enhancement Algorithm Based on Retinex Theory [J].Journal of Chongqing Technology and Business University(Natural Science Edition),2023,40(6):61-67.
[27]FU Z,YANG Y,TU X,et al.Learning a Simple Low-light Image Enhancer from Paired Low-light Instances [C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:22252-22261.
[28]LI J,FENG X,HUA Z.Low-Light Image Enhancement via Progressive-Recursive Network [J].IEEE Transactions on Circuits and Systems for Video Technology,2021,31(11):4227-4240.
[29]CHOLLET F.Xception:Deep Learning with Depthwise Separable Convolutions [C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.2017:1800-1807.
[30]CHARBONNIER P,BLANC-FERAUD L,AUBERT G,et al.Two deterministic half-quadratic regularization algorithms for computed imaging[C]//Proceedings of 1st International Confe-rence on Image Processing.1994:168-172.
[31]WANG Z,BOVIK A C,SHEIKH H R,et al.Image quality assessment:from error visibility to structural similarity [J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[32]LIU C,WU F,WANG X.EFINet:Restoration for Low-Light Images via Enhancement-Fusion Iterative Network [J].IEEE Transactions on Circuits and Systems for Video Technology,2022,32(12):8486-8499.
[33]ZHANG Y,DI X,WU J,et al.Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions [J].arXiv:2304.02978,2023.
[34]WANG S,ZHENG J,HU H,et al.Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination Images [J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[35]CAI J,GU S,ZHANG L.Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images [J].IEEE Tran-sactions on Image Processing,2018,27(4):2049-2062.
[36]LEE C,LEE C,KIM C S.Contrast enhancement based on layered difference representation of 2D histograms [J].IEEE Transactions on Image Processing,2013,22(12):5372-5384.
[37]GUO X,LI Y,LING H.LIME:Low-light image enhancement via illumination map estimation [J].IEEE Transactions on Image Processing,2016,26(2):982-993.
[38]MA K,ZENG K,WANG Z.Perceptual quality assessment for multi-exposure image fusion [J].IEEE Transactions on Image Processing,2015,24(11):3345-3356.
[39]WANG S,ZHENG J,HU H M,et al.Naturalness preserved enhancement algorithm for non-uniform illumination images [J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[40]MITTAL A,SOUNDARARAJAN R,BONIKA C.Making a“completely blind” image quality analyzer[J].IEEE Signal Processing Letters,2012,20(3):209-212.
[41]HUYNH-THU Q,GHANBARI M.Scope of validity of PSNR in image/video quality assessment [J].Electronics Letters,2008,44(13):800-801.
[42]ZHANG R,ISOLA P,EFROS A,et al.The Unreasonable Effectiveness of Deep Features as a Perceptual Metric [J].arXiv:1801.03924,2018.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发