计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 147-154.doi: 10.11896/jsjkx.221200074

• 计算机图形学&多媒体 • 上一篇    下一篇

一种自适应去噪保真的无监督暗光图像增强模型

高仁, 郝世杰, 郭艳蓉   

  1. 合肥工业大学计算机与信息学院 合肥230601
  • 收稿日期:2022-12-12 修回日期:2023-05-19 出版日期:2024-03-15 发布日期:2024-03-13
  • 通讯作者: 郝世杰(hfut.hsj@gmail.com)
  • 作者简介:(hfut.hsj@gmail.com)
  • 基金资助:
    国家自然科学基金(62172137)

Unsupervised Low-light Image Enhancement Model with Adaptive Noise Suppression and Detail Preservation

GAO Ren, HAO Shijie, GUO Yanrong   

  1. School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230601,China
  • Received:2022-12-12 Revised:2023-05-19 Online:2024-03-15 Published:2024-03-13
  • About author:GAO Ren,born in 1997,postgraduate.His main research interests include image processing and pattern recognition.HAO Shijie,born in 1983,Ph.D,professor,is a member of CCF(No.77721M).His main research interests include image processing and pattern recognition.
  • Supported by:
    National Natural Science Foundation of China(62172137).

摘要: 暗光环境下成像往往受到低照度和成像噪声等多种因素干扰,所得图片的视觉质量往往较低。当前各类暗光增强方法多侧重于改善可视度,却常忽略了保持增强结果真实感这一同样重要的目标。为解决该问题,提出了一种自适应去噪保真的无监督暗光图像增强方法,旨在高效便捷地实现改善图像可视度和去噪保真两个目标。模型由暗光增强阶段和去噪保真阶段组成。在暗光增强阶段,构建无监督图像分解模块和光照增强模块,实现改善可视度的目标;在去噪保真阶段,基于前一阶段所得的光照分布来自动构造成对训练数据,驱动去噪模块抑制原本昏暗处的噪声并保持原本明亮处的细节,实现增强结果保真的目标。实验结果表明,相比其他暗光增强方法,所提方法在改善可视度和去噪保真之间能够取得良好的均衡。该模型无须事先采集或准备“昏暗-明亮”成对图像来进行训练,且具有较小的模型尺寸和较快的计算速度,实用性良好。

关键词: 暗光图像, 光照增强, 噪声抑制, 图像分解

Abstract: The visual quality of images taken under low-light environment is usually low,due to many factors such as low lightness and imaging noise.Current low-light image enhancement methods have a common limitation that they only focus on improving lightness condition and suppressing noise,but neglect to preserve image details.To solve this problem,an unsupervised low light image enhancement method is proposed in this paper,aiming to improve the visibility and preserve the fidelity of an image with good efficiency.The model consists of two stages,i.e.,low-light enhancement and noise suppression.In the first stage,an unsupervised image decomposition module and a lightness enhancement module are constructed to achieve the goal of improving visibility.In the second stage,under the guidance of the illumination distribution of an image,we synthesize pairwise training data and train the denoising network to depress the imaging noise from the originally-dim regions and preserve the image details of the originally-bright regions.Compared with other methods,experimental results show that our method achieves better balance between the goals of visibility improvement and fidelity preservation.In addition,our method can be attractive in real-world applications,as it does not need to collect bright-dim image pairs,and it has small model size and fast calculation speed.

Key words: Low-light image, Lightness enhancement, Noise suppression, Image decomposition

中图分类号: 

  • TP391
[1]CAI B L,XU X M,GUO K L,et al.A Joint Intrinsic-Extrinsic Prior Model for Retinex[C]//International Conference on Computer Vision(ICCV).IEEE,2017:4020-4029.
[2]FU X Y,ZENG D L,HUANG Y,et al.A fusion-based enhancing method for weakly illuminated images[J].Signa Proces-sing,2016,129:82-96.
[3]LI C Y,GUO C L,HAN LH,et al.Low-Light Image and Video Enhancement Using Deep Learning:A Survey[J].arXiv:2104.10729,2021.
[4]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.
[5]GUO X J,LI Y,LING H B.LIME:Low-Light Image Enhancement via Illumination Map Estimation[J].IEEE Transactions on Image Processing,2017,26(2):982-993.
[6]LI M D,LIU J Y,YANG W H,et al.Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model[J].IEEE Transactions on Image Processing,2018,27(6):2828-2841.
[7]ZHANG Y H,ZHANG J W,GUO X J.Kindling the Darkness:A Practical Low-light Image Enhancer[C]//ACM International Conference on Multimedia,Association for Computing Machi-nery.2019:1632-1640.
[8]WEI C,WANG W J,YANG W H,et al.Deep Retinex Decomposition for Low-Light Enhancement[C]//British Machine Vision Conference.IEEE,2018:4020-4029.
[9]WANG R X,ZHANG Q,FU C W,et al.Underexposed PhotoEnhancement Using Deep Illumination Estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2019:6842-6850.
[10]JIANG Y F,GONG X Y,LIU D,et al.EnlightenGAN:Deep Light Enhancement Without Paired Supervision[J].IEEE Transactions on Image Processing,2021,30:2340-2349.
[11]LEE C,LEE C,KIM C S.Contrast Enhancement Based on La-yered Difference Representation of 2D Histograms[J].IEEE Transactions on Image Processing,2013,22(12):5372-5384.
[12]REN X T,YANG W H,CHENG WH,et al.LR3M:Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model[J].IEEE Transactions on Image Processing,2020,29:5862-5876.
[13]HAO S J,GUO Y R,WEI Z.Lightness-aware contrast enhancement for images with different illumination conditions[J].Multimedia Tools and Application,2019,78:3817-3830.
[14]HAO S J,HAN X,GUO Y R,et al.Low-Light Image Enhancement With Semi-Decoupled Decomposition[J].IEEE Transactions on Multimedia,2020,22(12):3025-3038.
[15]REN W Q,LIU S F,XU Q Q,et al.Low-Light Image Enhancement via a Deep Hybrid Network[J].IEEE Transactions on Image Processing,2019,28(9):4364-4375.
[16]MA K D,DUANMU Z F,ZHU H W,et al.Deep Guided Lear-ning for Fast Multi-Exposure Image Fusion[J].IEEE Transactions on Image Processing,2019,29:2808-2819.
[17]MA K D,LI H,YONG H W,et al.Robust Multi-ExposureImage Fusion:A Structural Patch Decomposition Approach[J].IEEE Transactions on Image Processing,2017,26(5):2519-2532.
[18]YANG W H,WANG S Q,FANG Y M,et al.From Fidelity to Perceptual Quality:A Semi-Supervised Approach for Low-Light Image Enhancement[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2020:3060-3069.
[19]CHEN C,CHEN Q F,XU J,et al.Learning to See in the Dark[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.2018:3291-3300.
[20]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing and Computer Assisted Intervention.2015:234-241.
[21]HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009:1956-1963.
[22]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//International Conference on Learning Representations.2014:1956-1963.
[23]GUO C L,LI C Y,GUO J C,et al.Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2020:1777-1786.
[24]CAI J R,GU S H,ZHANG L.Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images[J].IEEE Transactions on Image Processing,2018,27(4):2049-2062.
[25]LV F F,LU F,WU J H,et al.MBLLEN:Low-Light Image/Video Enhancement Using CNNs[C]//British Machine Vision Conference.2018.
[26]WANG S H,ZHENG J,HU H M,et al.Naturalness preserved enhancement algorithm for non-uniformillumination images[J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[27]FU X Y,LIAO Y H,ZENG D L,et al.A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation[J].IEEE Transactions on Image Proces-sing,2015,24(12):4965-4977.
[28]ZHU A Q,ZHANG L,SHEN Y,et al.Zero-Shot Restoration of Underexposed Images via Robust Retinex Decomposition[C]//2020 IEEE International Conference on Multimedia and Expo(ICME).IEEE,2020:1-6.
[29]DABOV K,FOI A,KATKOVNIK V,et al.Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080-2095.
[30]ZHANG K,ZUO W M,CHEN Y J,et al.Beyond a Gaussian Denoiser:Residual Learning of Deep CNN for Image Denoising[J].IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[31]YU S,PARK B,JEONG J.Deep Iterative Down-Up CNN for Image Denoising[C]//2019 IEEE/CVF Conference on Compu-ter Vision and Pattern Recognition Workshops(CVPRW).IEEE.2019:2095-2103.
[32]SHEN R H,ZHOU M R,LING S.Image Enhancement Technology Based on Improved FA Algorithm and Incomplete Beta Function[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2023,40(2):57-63.
[33]WANG M M,PENG D L Retinex-ADNet:a Low-light Image Enhancement System[J].Journal of Chinese Computer Systems.2022,43(2):367-371.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!