摘 要：为解决低光图像的亮度低、对比度弱等一系列降质问题，文章提出一种全新的网络架构用于低光图像增强。整个网络包含分解、去噪、和增强三个子网络，分解网络将图像分解成光照图和反射图，去噪网络在频域上对反射图进行去噪，增强网络通过多次卷积操作对光照图进行增强，最后将去噪后的反射图和增强后的光照图逐像素相乘得到结果图。实验证明，文章提出的方法可以有效地提升亮度和对比度、去除噪声，在主客观评价指标上有明显优势。
关键词：Retinex；全卷积网络；低光图像增强；损失函数；傅里叶变换
DOI:10.19850/j.cnki.2096-4706.2022.17.001
中图分类号：TP751 文献标识码：A 文章编号：2096-4706（2022）17-0001-07
Low Light Image Enhancement Method for Full Convolutional Network Based on Retinex Theory
YU Yaqi, YANG Menglong
(School of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, China)
Abstract: In order to solve a series of degradation problems such as low brightness and weak contrast of low light images, this paper proposes a new network architecture to enhance the low light images. The whole network includes three sub networks: decomposition, denoising and enhancement. The decomposition network decomposes the image into illumination image and reflection image. The denoising network denoises the reflection image in the frequency domain. The enhancement network enhances the illumination map through several convolution operations. Finally, the denoised reflection image and the enhanced illumination image are multiplied pixel by pixel to obtain the result image. Experiments show that the proposed method in this paper can effectively improve the brightness and contrast, remove noise and it has obvious advantages in subjective and objective evaluation indexes.
Keywords: Retinex; full convolution network; low light image enhancement; loss function; Fourier transform
参考文献：
[1] KIM Y T.Contrast Enhancement Using Brightness Preserving Bi-Histogram Equalization [J].IEEE Transactions on Consumer Electronics，1997，43（1）：1-8.
[2] PISANO E D，ZONG S，HEMMINGER B M，et al.Contrast Limited Adaptive Histogram Equalization Image Processing to Improve the Detection of Simulated Spiculations in Dense Mammograms [J].J Digit Imaging，1998，11（4）：193-200.
[3] LAND E H.The Retinex Theory of Color Vision [J].Scientific American，1977，237（6）：108-128.
[4] JOBSON D J，RAHMAN Z，WOODELL G A.Properties and Performance of a Center/Surround Retinex [J].IEEE Trans Image Process，1997，6（3）：451-462.
[5] JOBSON D J，RAHMAN Z，WOODELL G A.A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes [J].IEEE Trans Image Process，1997，6（7）：965-976.
[6] FU X Y，ZENG D L，HUANG Y，et al.A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）.Las Vegas：IEEE，2016：2782-2790.
[7] GUO X J ，LI Y ，LING H B.Lime：Low-Light Image Enhancement Via Illumination Map Estimation [J].IEEE Trans Image Process，2016，26（2）：982-993.
[8] KOSTADIN D，ALESSANDRO F，VLADIMIR K，et al.Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering [J].IEEE Trans Image Process，2007，16（8）：2080-95.
[9] ZHANG K，ZUO W M，CHEN Y J，et al.Beyond a Gaussian Denoiser：Residual Learning of Deep Cnn for Image Denoising [J].IEEE Trans Image Process，2017，26（7）：3142-3155.
[10] SALMON J，HARMANY Z，DELEDALLE C-A，et al.Poisson Noise Reduction with Non-Local Pca [J].J Math Imaging Vis，2014，48（2）：279-294.
[11] DONG C，LOY C C，HE K M，et al.Image SuperResolution Using Deep Convolutional Networks [J].IEEE Trans Pattern Anal Mach Intell，2016，38（2）：295-307.
[12] HARIS M，SHAKHNAROVICH G，UKITA N.Deep Back-Projection Networks for Super-Resolution [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：1664-1673.
[13] MAO X J，SHEN C H，YANG Y B.Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks With Symmetric Skip Connections [J/OL].arXiv：1603.09056 [cs.CV].[2022-05-23].https://arxiv.org/abs/1603.09056.
[14] ZHANG K，ZUO W M，CHEN Y J，et al.Beyond a Gaussian Denoiser：Residual Learning of Deep Cnn for Image Denoising [J].IEEE Trans Image Process，2017，26（7）：3142-3155.
[15] LORE K G，AKINTAYO A，SARKAR S.Llnet：a deep autoencoder approach to Natural Low-Light Image Enhancement [J]. Pattern Recognit，2017，61：650-662.
[16] WEI C，WANG W J，YANG W H，et al.Deep Retinex Decomposition for Low-Light Enhancement [J/OL].arXiv：1808.04560 [cs.CV].[2022-05-27].https://arxiv.org/abs/1808.04560.
[17] ZHANG Y H，ZHANG J W，GUO X J.Kindling the Darkness：A Practical Low-Light Image Enhancer [C]//MM'19： Proceedings of the 27th ACM International Conference on Multimedia. New York：Association for Computing Machinery，2019：1632-1640.
[18] WANG L W，LIU Z S，SIU W C，et al.Lightening Network for Low-Light Image Enhancement [J].IEEE Transactions on Image Processing，2020，29：7984-7996.
[19] 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）. Seattle：IEEE，2020：1777-1786.
[20] 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.
[21] CHEN Y S，WANG Y C，KAO M H，et al.Deep Photo Enhancer：Unpaired Learning for Image Enhancement from Photographs with GANs [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：6306-6314.
[22] HE K M，ZHANG X Y，REN S Q，et al.Deep Residual Learning for Image Recognition [J/OL].arXiv：1512.03385 [cs.CV]. [2022-06-15].https://arxiv.org/abs/1512.03385.
[23] LI C Y，GUO J C，PORIKLI F，et al.LightenNet： A Convolutional Neural Network for Weakly Illuminated Image Enhancement [J].Pattern Recognition Letters，2018，104：15-22.
[24] RONNEBERGER O，FISCHER P，BROX T.U-Net： Convolutional Networks for Biomedical Image Segmentation [C]// International Conference on Medical Image Computing and ComputerAssisted Intervention.Munich：Springer，2015：234-241.
[25] SPRINGENBERG J T，DOSOVITSKIY A，BROX T，et al.Striving For Simplicity：The All Convolutional Net [J/ OL].arXiv：1412.6806 [cs.LG].[2022-05-07].https://arxiv.org/ abs/1412.6806v3?source=post_page.
[26] FU X Y，ZENG D L，HUANG Y，et al.A FusionBased Enhancing Method for Weakly Illuminated Images [J].Signal Processing，2016，129（C）：82-96.
[27] DONG X，WANG G，PANG Y，et al.Fast Efficient Algorithm for Enhancement of Low Lighting Video [C]//2011 IEEE International Conference on Multimedia and Expo.Barcelona：IEEE， 2011：1-6.
[28] WANG S H，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.
[29] 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.Salt Lake City：IEEE，2018：3291-3300.
[30] LEE C W，LEE C，KIM C S.Contrast Enhancement Based on Layered Difference Representation [C]//2012 19th IEEE International Conference on Image Processing.Orlando：IEEE，2013：965-968.
[31] MA K D，ZENG K，WANG Z.Perceptual Quality Assessment for Multi-Exposure Image Fusion [J].IEEE Transactions on Image Processing，2015，24（11）：3345-3356.
作者简介：余雅琪（1997—），女，土家族，重庆人，硕士研究生，研究方向：低光图像处理；通讯作者：杨梦龙（1983—），男，汉族，四川成都人，副研究员，博士研究生，研究方向：计算机视觉，模式识别，图像处理。