计算机科学 ›› 2023, Vol. 50 ›› Issue (1): 123-130.doi: 10.11896/jsjkx.211100058
王斌, 梁宇栋, 刘哲, 张超, 李德玉
WANG Bin, LIANG Yudong, LIU Zhe, ZHANG Chao, LI Deyu
摘要: 在低质图像降质问题中,亮度偏离(如图像偏亮及偏暗)是较为常见的图像降质现象。基于全监督学习的图像增强方法面临训练数据难以获取或获取成本过高、训练数据和应用场景不一致的困境。针对以上问题,提出了一种能够克服数据依赖和亮度自适应的无监督图像增强方法。方法的具体细节为:针对图像去雾与低光增强任务,设计了一个基于通道与像素注意力的深度卷积网络,对增强图像与输入图像进行比较,采用亮度饱和度、空间一致性、照明平滑度、伪标签监督损失等多种无监督损失函数,在保证增强图像与输入图像一致性的同时,调节图像的亮度偏离程度,有效提高图像质量。实验结果表明,所提方法在客观指标及视觉效果上不仅优于传统方法和基于无监督学习的方法,甚至优于近年来的全监督图像增强方法。将所提方法与5种图像去雾方法及4种低光增强方法分别进行对比,相比性能次优的方法,其在图像去雾任务的Reside数据集上,PSNR和SSIM值分别提高了2.8 dB和0.01;在低光增强任务的SICE数据集上,PSNR和SSIM分别提高了0.56 dB和0.01。结果表明,所提无监督图像去雾与低光增强算法能够有效调节图像的亮度偏离程度,重建了亮度正常、细节清晰、对比度较好的增强复原图像,较为有效地克服了当前底层视觉任务数据难以获取、训练数据与应用数据不一致、存在域迁移的难题,提升了算法在应用中的适用性。
中图分类号:
[1]ABDULLAH-AL-WADUD M,KABIR M H,DEWAN M A A,et al.A dynamic histogram equalization for image contrast enhancement[J].IEEE Transactions on Consumer Electronics,2007,53(2):593-600. [2]HE K,SUN J,TANG X.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(12):2341-2353. [3]LAND E H.The retinex theory of color vision[J].ScientificAmerican,1977,237(6):108-129. [4]CAI B,XU X,JIA K,et al.Dehazenet:An end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198. [5]WEI C,WANG W,YANG W,et al.Deep retinex decomposition for low-light enhancement[J].arXiv:1808.04560,2018. [6]YAN L,ZHENG W,GOU C,et al.Feature Aggregation Attention Network for Single Image Dehazing[C]//2020 IEEE International Conference on Image Processing(ICIP).IEEE,2020:923-927. [7]PIZER S M,JOHSON R E,ERICKSEN J P,et al.Contrast-li-mited adaptive histogram equalization:Speed and effectiveness[C]//Proceedings of the First Conference on Visualization in Biomedical Computing,Atlanta,Georgia.1990,337:1. [8]JOBSON D J,RAHMAN Z,WOODELL G A.Properties andperformance of a center/surround retinex[J].IEEE Transactions on Image Processing,1997,6(3):451-462. [9]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. [10]CAI J,GU S,ZHANG L.Learning a deep single image contrast enhancer from multi-exposure images[J].IEEE Transactions on Image Processing,2018,27(4):2049-2062. [11]REN W,LIU S,MA L,et al.Low-light image enhancement via a deep hybrid network[J].IEEE Transactions on Image Proces-sing,2019,28(9):4364-4375. [12]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. [13]YANG W,WANG S,FANG Y,et al.From fidelity to perceptual quality:A semi-supervised approach for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:3063-3072. [14]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. [15]BERMAN D,AVIDAN S.Non-local image dehazing[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:1674-1682. [16]ZHANG H,PATEL V M.Densely connected pyramid dehazing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3194-3203. [17]LI L,DONG Y,REN W,et al.Semi-supervised image dehazing[J].IEEE Transactions on Image Processing,2019,29:2766-2779. [18]GANDELSMAN Y,SHOCHER A,IRANI M.“Double-DIP”:Unsupervised Image Decomposition via Coupled Deep-Image-Priors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:11026-11035. [19]CHEN Y S,WANG Y C,KAO M H,et al.Deep photo enhancer:Unpaired learning for image enhancement from photographs with gans[C]//Proceedings of the IEEE Conference on Compu-ter Vision and Pattern Recognition.2018:6306-6314. [20]DING Y J,HUANG S.An Improved Generative AdversarialNetwork for Image Dehazing[J].Computer Engineering,2022,48(6):207-212. [21]HE T,YU S M,XU H.Single Image Dehazing Method Based on Conditional Generative Adversarial Network and Knowledge Distillation[J].Computer Engineering,2022,48(4):165-172. [22]GODARD C,MAC AODHA O,BROSTOW G J.Unsupervised monocular depth estimation with left-right consistency[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:270-279. [23]KRULL A,BUCHHOLZ T O,JUG F.Noise2void-learning denoising from single noisy images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:2129-2137. [24]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. [25]LI B,REN W,FU D,et al.Reside:A benchmark for singleimage dehazing[J].arXiv:1712.04143,2017. [26]GEIGER A,LENZ P,STILLER C,et al.Vision meets robotics:The kitti dataset[J].The International Journal of Robotics Research,2013,32(11):1231-1237. [27]FU X,ZENG D,HUANG Y,et al.A weighted variational model for simultaneous reflectance and illumination estimation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:2782-2790. [28]GUO X,LI Y,LING H.LIME:Low-light image enhancementvia illumination map estimation[J].IEEE Transactions on image processing,2016,26(2):982-993. [29]ULYANOV D,VEDALDI A,LEMPITSKY V.Deep image prior[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:9446-9454. |
[1] | 蔡肖, 陈志华, 盛斌. 基于移位窗口金字塔Transformer的遥感图像目标检测 SPT:Swin Pyramid Transformer for Object Detection of Remote Sensing 计算机科学, 2023, 50(1): 105-113. https://doi.org/10.11896/jsjkx.211100208 |
[2] | 李雪辉, 张拥军, 史殿习, 徐化池, 史燕燕. 融合注意力特征的无锚框视觉目标跟踪方法 AFTM:Anchor-free Object Tracking Method with Attention Features 计算机科学, 2023, 50(1): 138-146. https://doi.org/10.11896/jsjkx.211000083 |
[3] | 孙凯丽, 罗旭东, 罗有容. 预训练语言模型的应用综述 Survey of Applications of Pretrained Language Models 计算机科学, 2023, 50(1): 176-184. https://doi.org/10.11896/jsjkx.220800223 |
[4] | 郑诚, 梅亮, 赵伊研, 张苏航. 基于双向注意力机制和门控图卷积网络的文本分类方法 Text Classification Method Based on Bidirectional Attention and Gated Graph Convolutional Networks 计算机科学, 2023, 50(1): 221-228. https://doi.org/10.11896/jsjkx.211100095 |
[5] | 李小玲, 吴昊天, 周涛, 鲁辉. 一种基于强化学习的口令猜解模型 Password Guessing Model Based on Reinforcement Learning 计算机科学, 2023, 50(1): 334-341. https://doi.org/10.11896/jsjkx.211100001 |
[6] | 宋杰, 梁美玉, 薛哲, 杜军平, 寇菲菲. 基于无监督集群级的科技论文异质图节点表示学习方法 Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level 计算机科学, 2022, 49(9): 64-69. https://doi.org/10.11896/jsjkx.220500196 |
[7] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
[8] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[9] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
[10] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[11] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
[12] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
[13] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
[14] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
[15] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
|