单幅图像去雨数据集和深度学习算法的联合评估与展望

胡明娣; 吴怡; 宋尧; 杨静冰; 张瑞芳; 王红; 孟德宇

doi:10.11834/jig.211153

综述 | 浏览量 : 0 下载量: 814 CSCD: 2

PDF
导出
分享
收藏
专辑

单幅图像去雨数据集和深度学习算法的联合评估与展望
The integrated evaluation and review of single image rain removal based datasets and deep learning methods
2022年27卷第5期页码：1359-1391
收稿：2021-12-01，

修回：2022-3-3，

录用：2022-3-10，

纸质出版：2022-05-16
DOI： 10.11834/jig.211153
稿件说明：

移动端阅览

胡明娣, 吴怡, 宋尧, 杨静冰, 张瑞芳, 王红, 孟德宇. 单幅图像去雨数据集和深度学习算法的联合评估与展望[J]. 中国图象图形学报, 2022,27(5):1359-1391. DOI： 10.11834/jig.211153.

Mingdi Hu, Yi Wu, Yao Song, Jingbing Yang, Ruifang Zhang, Hong Wang, Deyu Meng. The integrated evaluation and review of single image rain removal based datasets and deep learning methods[J]. Journal of Image and Graphics, 2022, 27(5): 1359-1391. DOI： 10.11834/jig.211153.

摘要

雨天会影响室外图像捕捉的质量，进而引起户外视觉任务性能下降。基于深度学习的单幅图像去雨研究因算法性能优越而引起了大家的关注，并且聚焦点集中在数据集的质量、图像去雨方法、单幅图像去雨后续高层任务的研究和性能评价指标等方面。为了方便研究者快速全面了解该领域，本文从上述4个方面综述了基于深度学习的单幅图像去雨的主流文献。依据数据集的构建方式将雨图数据集分为4类：基于背景雨层简单加和、背景雨层复杂融合、生成对抗网络(generative adversarial network，GAN)数据驱动合成的数据集，以及半自动化采集的真实数据集。依据任务场景、采取的学习机制以及网络设计对主流算法分类总结。综述了面向单任务和联合任务的去雨算法，单任务即雨滴、雨纹、雨雾和暴雨的去除；联合任务即雨滴和雨纹、所有噪声去除。综述了学习机制和网络构建方式(比如: 卷积神经网络(convolutional neural network，CNN)结构多分支组合，GAN的生成结构，循环和多阶段结构，多尺度结构，编解码结构，基于注意力，基于Transformer)以及数据模型双驱动的构建方式。综述了单幅图像去雨后续高层任务的研究文献和图像去雨算法性能的评价指标。通过合成数据集和真实数据集上的综合实验对比，证实了领域知识隐式引导网络构建可以有效提升算法性能，领域知识显式引导正则化网络的学习有潜力进一步提升算法的泛化性。最后，指出单幅图像去雨工作目前面临的挑战和未来的研究方向。

Abstract

The visual quality of captured images in rainy weather conditions is constrained to the outdoor vision degradation. It is essential to design relevant rain removal algorithms. Due to the lack of temporal information

single image rain removal is challenging compared to video-based rain removal. The target of single image rain removal analysis is to restore the rain-removed background image from the corresponding rain-affected image. Current deep learning based vision tasks construct diverse data-driven frameworks like single image rain removal task via multiple network modules. Current research tasks are focusing on the quality of datasets

the design of single image deraining algorithms

the subsequent high-level vision tasks

and the design of performance evaluation metrics. Specifically

the quality of rain datasets largely affects the performance of deep learning based single image deraining methods

since the generalization ability of deep single image rain removal is highly related to the domain gap between synthesized training dataset and real testing dataset. Besides

rain removal plays an important preprocessing role in outdoor visual tasks because its result would affect the performance of the subsequent visual task. Additionally

the design of image quality assessment (IQA) metrics is quite important for the fair quantitative analysis of human perception of image quality in general image restoration tasks. We conducted critical literature review for deep learning based single image rain removal from the four aspects as mentioned below: 1) dataset generation in rain weather conditions; 2) representative deep neural network based single image rain removal algorithms; 3) the research of the downstream high-level task in rainy days and 4) performance metrics for evaluating single image rain removal algorithms. Specifically

in terms of the generation manners

the current rain image datasets are roughly divided into four categories as following: 1) synthesizing rain streaks based on photo-realistic rendering technique and then adding them on clear images based on simple physical model; 2) constructing rain images based on complex physical model via manual parameters setting; 3) generating rain images based on generative adversarial network (GAN); 4) collecting paired rain-free/rain-affected images by shooting different scenarios and adjusting camera parameters. We reviewed the download links of the existing representative rain image datasets. For deep learning based single image rain removal methods

we review the supervised and semi-/unsupervised rain removal methods for single task and joint tasks in terms of task scenarios

learning mechanisms and network design. Here

single task is relevant to rain drop removal

rain streak

rain fog

heavy rain; and the integrated analyses of removal of rain drop and rain streak

or multiple noises removal. Furthermore

we overview the construction manners of representative network architectures

including simplified convolutional neural networks based (CNNs-based) multi-branches architecture

GAN-based mechanism

recurrent and multi-stage framework

multi-scale architecture

the integration of encoder-decoder modules

attention mechanism or transformer based module as well as model-driven and data-driven learning manners. Since the implicit or explicit embedding of domain knowledge can promote network construction

we provide a detailed survey in the context of the relationship between rain removal methods and domain knowledge.We illustrated that the domain knowledge and the learning of benched networks has the potential to improve the generalization performance of single image rain removal algorithm further. Based on the real high-level outdoor vision tasks in rain weather

it would be meaningful to use the joint processing strategies of low-level and high-level tasks and the customized construction of rainy datasets. Meanwhile

we reviewed and clarified some related literatures of high-level computer vision tasks and comprehensively analyzed the performance evaluation metrics in the context of full-reference metrics and non-reference metrics. We analyzed the potential challenges of single image rain removal further in the context of feasible benchmark datasets construction

future fair evaluation metrics designing

and the optimized integration of rain removal and high-level vision tasks.

关键词

Keywords

references

Arbeláez P, Maire M, Fowlkes C and Malik J. 2011. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5): 898-916[DOI: 10.1109/TPAMI.2010.161]

Athar S and Wang Z. 2019. A comprehensive performance evaluation of image quality assessment algorithms. IEEE Access, 7: 140030-140070[DOI: 10.1109/ACCESS.2019.2943319]

Caesar H, Bankiti V, Lang A H, Vora S, Liong V E, Xu Q, Krishnan A, Pan Y, Baldan G and Beijbom O. 2020. nuScenes: a multimodal dataset for autonomous driving//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 11618-11628[ DOI: 10.1109/CVPR42600.2020.01164 http://dx.doi.org/10.1109/CVPR42600.2020.01164 ]

Chai G Q, Wang D W, Lu B and Li Z. 2021. Lightweight dense network based on attention mechanism for single-image deraining[J/OL]. [2021-09-15]. Journal of Beijing University of Aeronautics and Astronautics, 1-8

柴国强, 王大为, 芦宾, 李竹. 2021. 基于注意机制的轻量化稠密网络单幅图像去雨[J/OL]. [2021-09-15] . 北京航空航天大学学报, 1-8. https://kns.cnki.net/kcms/detail/detail.aspx?doi=10.13700/j.bh.1001-5965.2021.0294 https://kns.cnki.net/kcms/detail/detail.aspx?doi=10.13700/j.bh.1001-5965.2021.0294

Chen C H and Li H. 2021. Robust representation learning with feedback for single image deraining//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 7738-7747[ DOI: 10.1109/CVPR46437.2021.00765 http://dx.doi.org/10.1109/CVPR46437.2021.00765 ]

Chen S M, Chen W and Yin Z. 2022. Research status and prospect of single image rain removal algorithm. Application Research of Computers, 39(1): 9-17

陈舒曼, 陈玮, 尹钟. 2022. 单幅图像去雨算法研究现状及展望. 计算机应用研究, 39(1): 9-17)[DOI: 10.19734/j.issn.1001-3695.2021.05.0209]

Chen X Q, Zhang Q Y, Lin M H, Yang G Y and He C. 2019. No-reference color image quality assessment: from entropy to perceptual quality. EURASIP Journal on Image and Video Processing, 2019(1): 77[DOI: 10.1186/s13640-019-0479-7]

Cho J, Jang H, Ha N, Lee S, Park S and Sohn K. 2019. Deep unsupervised learning for rain streak removal using time-varying rain streak scene. Journal of Korea Multimedia Society, 22(1): 1-9[DOI: 10.9717/kmms.2019.22.1.001]

Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S and Schiele B. 2016. The cityscapes dataset for semantic urban scene understanding//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE: 3213-3223[ DOI: 10.1109/CVPR.2016.350 http://dx.doi.org/10.1109/CVPR.2016.350 ]

Deng S, Wei M Q, Wang J, Feng Y D, Liang L M, Xie H R, Wang F L and Wang M. 2020. Detail-recovery image deraining via context aggregation networks//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 14548-14557[ DOI: 10.1109/CVPR42600.2020.01457 http://dx.doi.org/10.1109/CVPR42600.2020.01457 ]

Ding J J, Guo H L, Zhou H, Yu J, He X X and Jiang B. 2021a. Distributed feedback network for single-image deraining. Information Sciences, 572: 611-626[DOI: 10.1016/j.ins.2021.02.080]

Ding K Y, Ma K D, Wang S Q and Simoncelli E P. 2021b. Comparison of full-reference image quality models for optimization of image processing systems. International Journal of Computer Vision, 129(4): 1258-1281[DOI: 10.1007/s11263-020-01419-7]

Du Y J, Xu J, Qiu Q, Zhen X T and Zhang L. 2020a. Variational image deraining//Proceedings of 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). Snowmass, USA: IEEE: 2395-2404[ DOI: 10.1109/WACV45572.2020.9093393 http://dx.doi.org/10.1109/WACV45572.2020.9093393 ]

Du Y J, Xu J, Zhen X T, Cheng M M and Shao L. 2020b. Conditional variational image deraining. IEEE Transactions on Image Processing, 29: 6288-6301[DOI: 10.1109/TIP.2020.2990606]

Fan Z W, Wu H F, Fu X Y, Huang Y and Ding X H. 2018. Residual-Guide Network for Single Image Deraining//Proceedings of the 26th ACM International Conference on Multimedia. Seoul, Korea(South): ACM: 1751-1759[ DOI: 10.1145/3240508.3240694 http://dx.doi.org/10.1145/3240508.3240694 ]

Fu X Y, Huang J B, Ding X H, Liao Y H and Paisley J. 2017a. Clearing the skies: a deep network architecture for single-image rain removal. IEEE Transactions on Image Processing, 26(6): 2944-2956[DOI: 10.1109/TIP.2017.2691802]

Fu X Y, Huang J B, Zeng D L, Huang Y, Ding X H and Paisley J. 2017b. Removing rain from single images via a deep detail network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 1715-1723[ DOI: 10.1109/CVPR.2017.186 http://dx.doi.org/10.1109/CVPR.2017.186 ]

Fu X Y, Liang B R, Huang Y, Ding X H and Paisley J. 2020. Lightweight pyramid networks for image deraining. IEEE Transactions on Neural Networks and Learning Systems, 31(6): 1794-1807[DOI: 10.1109/TNNLS.2019.2926481]

Fu X Y, Qi Q, Zha Z J, Zhu Y R and Ding X H. 2021. Rain streak removal via dual graph convolutional network//Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI). Palo Alto, USA: AAAI: 1352-1360

Gabarda S and Cristóbal G. 2007. Blind image quality assessment through anisotropy. Journal of the Optical Society of America A, 24(12): B42-B51[DOI: 10.1364/JOSAA.24.000B42]

Garg K and Nayar S K. 2006. Photorealistic rendering of rain streaks. ACM Transactions on Graphics, 25(3): 996-1002[DOI: 10.1145/1141911.1141985]

Geiger A, Lenz P, Stiller C and Urtasun R. 2013. Vision meets robotics: the KITTI dataset. The International Journal of Robotics Research, 32(11): 1231-1237[DOI: 10.1177/0278364913491297]

Geiger A, Lenz P and Urtasun R. 2012. Are we ready for autonomous driving? The KITTI vision benchmark suite//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA: IEEE: 3354-3361[ DOI: 10.1109/CVPR.2012.6248074 http://dx.doi.org/10.1109/CVPR.2012.6248074 ]

Hu X W, Fu C W, Zhu L and Heng P A. 2019. Depth-attentional features for single-image rain removal//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 8014-8023[ DOI: 10.1109/CVPR.2019.00821 http://dx.doi.org/10.1109/CVPR.2019.00821 ]

Huang H B, Yu A J and He R. 2021. Memory oriented transfer learning for semi-supervised image deraining//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 7728-7737[ DOI: 10.1109/CVPR46437.2021.00764 http://dx.doi.org/10.1109/CVPR46437.2021.00764 ]

Huynh-Thu Q and Ghanbari M. 2008. Scope of validity of PSNR in image/video quality assessment. Electronics Letters, 44(13): 800-801[DOI: 10.1049/el:20080522]

Jiang K, Wang Z Y, Yi P, Chen C, Huang B J, Luo Y M, Ma J Y and Jiang J J. 2020. Multi-scale progressive fusion network for single image deraining//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 8343-8352[ DOI: 10.1109/CVPR42600.2020.00837 http://dx.doi.org/10.1109/CVPR42600.2020.00837 ]

Jiang N F, Chen W L, Lin L Q and Zhao T S. 2021. Single image rain removal via multi-module deep grid network. Computer Vision and Image Understanding, 202: #103106[DOI: 10.1016/j.cviu.2020.103106]

Jin J C, Fatemi A, Lira W M P, Yu F G, Leng B, Ma R, Mahdavi-Amiri A and Zhang H. 2021. RaidaR: a rich annotated image dataset of rainy street scenes//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal, Canada: IEEE: 2951-2961[ DOI: 10.1109/ICCVW54120.2021.00330 http://dx.doi.org/10.1109/ICCVW54120.2021.00330 ]

Jin X, Chen Z B, Lin J X, Chen Z K and Zhou W. 2019. Unsupervised single image deraining with self-supervised constraints//Proceedings of 2019 IEEE International Conference on Image Processing (ICIP). Taipei, China: IEEE: 2761-2765[ DOI: 10.1109/ICIP.2019.8803238 http://dx.doi.org/10.1109/ICIP.2019.8803238 ]

Lee J H, Han M K, Ko D W and Suh I H. 2019. From big to small: multi-scale local planar guidance for monocular depth estimation[EB/OL]. [2021-09-23] . https://arxiv.53yu.com/pdf/1907.10326.pdf https://arxiv.53yu.com/pdf/1907.10326.pdf

Li B Y, Ren W Q, Fu D P, Tao D C, Feng D, Zeng W J and Wang Z Y. 2019a. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 28(1): 492-505[DOI: 10.1109/TIP.2018.2867951]

Li G B, He X, Zhang W, Chang H Y, Dong L and Lin L. 2018a. Non-locally enhanced encoder-decoder network for single image de-raining//Proceedings of the 26th ACM International Conference on Multimedia. Seoul, Korea(South): ACM: 1056-1064[ DOI: 10.1145/3240508.3240636 http://dx.doi.org/10.1145/3240508.3240636 ]

Li L D, Yan Y, Fang Y M, Wang S Q, Tang L and Qian J S. 2016a. Perceptual quality evaluation for image defocus deblurring. Signal Processing: Image Communication, 48: 81-91[DOI: 10.1016/j.image.2016.09.005]

Li L D, Zhou Y, Gu K, Yang Y Z and Fang Y M. 2020a. Blind realistic blur assessment based on discrepancy learning. IEEE Transactions on Circuits and Systems for Video Technology, 30(11): 3859-3869[DOI: 10.1109/TCSVT.2019.2947450]

Li R T, Cheong L F and Tan R T. 2017. Single image deraining using scale-aware multi-stage recurrent network[EB/OL]. [2021-11-01] . https://arxiv.53yu.com/pdf/1712.06830.pdf https://arxiv.53yu.com/pdf/1712.06830.pdf

Li R T, Cheong L F and Tan R T.2019b. Heavy rain image restoration: integrating physics model and conditional adversarial learning//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 1633-1642[ DOI: 10.1109/CVPR.2019.00173 http://dx.doi.org/10.1109/CVPR.2019.00173 ]

Li R T, Tan R T and Cheong L F. 2020b. All in one bad weather removal using architectural search//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 3172-3182[ DOI: 10.1109/CVPR42600.2020.00324 http://dx.doi.org/10.1109/CVPR42600.2020.00324 ]

Li S Y, Araujo I B, Ren W Q, Wang Z Y, Tokuda E K, Junior R H, Cesar-Junior R, Zhang J W, Guo X J and Cao X C. 2019c. Single image deraining: a comprehensive benchmark analysis//Proceedings of 2019 IEEE /CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 3833-3842[ DOI: 10.1109/CVPR.2019.00396 http://dx.doi.org/10.1109/CVPR.2019.00396 ]

Li S Y, Ren W Q, Zhang J W, Yu J K and Guo X J. 2019d. Single image rain removal via a deep decomposition-composition network. Computer Vision and Image Understanding, 186: 48-57[DOI: 10.1016/j.cviu.2019.05.003]

Li X, Wu J L, Lin Z C, Liu H and Zha H B. 2018b. Recurrent squeeze-and-excitation context aggregation net for single image deraining//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich, Germany: Springer: 262-277[ DOI: 10.1007/978-3-030-01234-2_16 http://dx.doi.org/10.1007/978-3-030-01234-2_16 ]

Li Y, Tan R T, Guo X J, Lu J B and Brown M S. 2016b. Rain streak removal using layer priors//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 2736-2744[ DOI: 10.1109/CVPR.2016.299 http://dx.doi.org/10.1109/CVPR.2016.299 ]

Liu D, Wen B H, Liu X M, Wang Z Y and Huang T S. 2018. When image denoising meets high-level vision tasks: a deep learning approach//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: AAAI Press: 842-848

Liu L X, Liu B, Huang H and Bovik A C. 2014. No-reference image quality assessment based on spatial and spectral entropies. Signal Processing: Image Communication, 29(8): 856-863[DOI: 10.1016/j.image.2014.06.006]

Liu R S, Jiang Z Y, Fan X and Luo Z X. 2020. Knowledge-driven deep unrolling for robust image layer separation. IEEE Transactions on Neural Networks and Learning Systems, 31(5): 1653-1666[DOI: 10.1109/TNNLS.2019.2921597]

Liu X, Suganuma M, Sun Z and OkataniT. 2019. Dual residual networks leveraging the potential of paired operations for image restoration//Proceedings of 2019 IEEE /CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 7000-7009[ DOI: 10.1109/CVPR.2019.00717 http://dx.doi.org/10.1109/CVPR.2019.00717 ]

Ma C, Yang C Y, Yang X K and Yang M H. 2017. Learning a no-reference quality metric for single-image super-resolution. Computer Vision and Image Understanding, 158: 1-16[DOI: 10.1016/j.cviu.2016.12.009]

Ma J P, Wu J J, Li L D, Dong W S, Xie X M, Shi G M and Lin W S. 2021. Blind image quality assessment with active inference. IEEE Transactions on Image Processing, 33: 3650-3663[DOI: 10.1109/TIP.2021.3064195]

Ma K D and Fang Y M. 2021. Image quality assessment in the modern age//Proceedings of the 29th ACM International Conference on Multimedia. ACM: 5664-5666[ DOI: 10.1145/3474085.3478870 http://dx.doi.org/10.1145/3474085.3478870 ]

Mittal A, Moorthy A K and Bovik A C. 2012. Blind/referenceless image spatial quality evaluator//Proceedings of 2011 Conference Record of the 45th Asilomar Conference on Signals, Systems and Computers (ASILOMAR). Pacific Grove, USA: IEEE: 723-727[ DOI: 10.1109/ACSSC.2011.6190099 http://dx.doi.org/10.1109/ACSSC.2011.6190099 ]

Mittal A, Soundararajan R and Bovik A C. 2013. Making a "Completely Blind" image quality analyze. IEEE Signal Processing Letters, 20(3): 209-212[DOI: 10.1109/LSP.2012.2227726]

Moorthy A K and Bovik A C. 2010. A two-step framework for constructing blind image quality indices. IEEE Signal Processing Letters, 17(5): 513-516[DOI: 10.1109/LSP.2010.2043888]

Mu P, Chen J, Liu R S, Fan X and Luo Z X. 2019. Learning bilevel layer priors for single image rain streaks removal. IEEE Signal Processing Letters, 26(2): 307-311[DOI: 10.1109/LSP.2018.2889277]

Ni S Q, Cao X Y, Yue T and Hu X M. 2021. Controlling the rain: from removal to rendering//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, USA: IEEE: 6324-6333[ DOI: 10.1109/CVPR46437.2021.00626 http://dx.doi.org/10.1109/CVPR46437.2021.00626 ]

Pan J S, Liu S F, Sun D Q, Zhang J W, Liu Y, Ren J, Li Z C, Tang J H, Lu H C, Tai Y W and Yang M H. 2018. Learning dual convolutional neural networks for low-level vision//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 3070-3079[ DOI: 10.1109/CVPR.2018.00324 http://dx.doi.org/10.1109/CVPR.2018.00324 ]

Qian R, Tan R T, Yang W H, Su J J and Liu J Y. 2018. Attentive generative adversarial network for raindrop removal from a single image//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 2482-2491[ DOI: 10.1109/CVPR.2018.00263 http://dx.doi.org/10.1109/CVPR.2018.00263 ]

Qin Q, Yan J K, Wang Q, Wang X, Li M Y and Wang Y Q. 2021. ETDNet: an efficient transformer deraining model. IEEE Access, 9: 119881-119893[DOI: 10.1109/ACCESS.2021.3108516]

Qiu Y R, Yao G L, Feng J and Cui H Y. 2021. Single image de-raining algorithm based on semi-supervised learning[J/OL]. [2021-06-11]. Journal of Computer Applications, 1-7

邱永茹, 姚光乐, 冯杰, 崔昊宇. 2021. 基于半监督学习的单幅图像去雨算法[J/OL]. [2021-06-11] . 计算机应用, 1-7. https://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFQ&dbname=CAPJLAST&filename=JSJY20210610002 https://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFQ&dbname=CAPJLAST&filename=JSJY20210610002

Quan R J, Yu X, Liang Y Z and Yang Y. 2021. Removing raindrops and rain streaks in one go//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 9143-9152[ DOI: 10.1109/CVPR46437.2021.00903 http://dx.doi.org/10.1109/CVPR46437.2021.00903 ]

Quan Y H, Deng S J, Chen Y X and Ji H. 2019. Deep learning for seeing through window with raindrops//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul, Korea(South): IEEE: 2463-2471[ DOI: 10.1109/ICCV.2019.00255 http://dx.doi.org/10.1109/ICCV.2019.00255 ]

Redmon J and Farhadi A. 2018. YOLOv3: an incremental improvement[EB/OL]. [2021-11-01] . https://arxiv.53yu.com/pdf/1804.02767.pdf https://arxiv.53yu.com/pdf/1804.02767.pdf

Ren D W, Zuo W M, Hu Q H, Zhu P F and Meng D Y. 2019. Progressive image deraining networks: a better and simpler baseline//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 3932-3941[ DOI: 10.1109/CVPR.2019.00406 http://dx.doi.org/10.1109/CVPR.2019.00406 ]

Ren S Q, He K M, Girshick R and Sun J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 1137-1149[DOI: 10.1109/TPAMI.2016.2577031]

Saad M A, Bovik A C and Charrier C. 2010. A DCT statistics-based blind image quality index. IEEE Signal Processing Letters, 17(6): 583-586[DOI: 10.1109/LSP.2010.2045550]

Schaefer G and Stich M. 2003. UCID: an uncompressed color image database//Proceedings of SPIE 5307, Storage and Retrieval Methods and Applications for Multimedia 2004. San Jose, USA: SPIE: 472-480[ DOI: 10.1117/12.525375 http://dx.doi.org/10.1117/12.525375 ]

Shao M W, Li L, Meng D Y and Zuo W M. 2021a. Uncertainty guided multi-scale attention network for raindrop removal from a single image. IEEE Transactions on Image Processing, 30: 4828-4839[DOI: 10.1109/TIP.2021.3076283]

Shao M W, Li L, Wang H and Meng D Y. 2021b. Selective generative adversarial network for raindrop removal from a single image. Neurocomputing, 426: 265-273[DOI: 10.1016/j.neucom.2020.06.134]

Silberman N, Hoiem D, Kohli P and Fergus R. 2012. Indoor segmentation and support inference from RGBD images//Proceedings of the 12th European Conference on Computer Vision. Florence, Italy: Springer: 746-760[ DOI: 10.1007/978-3-642-33715-4_54 http://dx.doi.org/10.1007/978-3-642-33715-4_54 ]

Su Z P, Zhang Y X, Zhang X P and Qi F. 2022. Non-local channel aggregation network for single image rain removal. Neurocomputing, 469: 261-272[DOI: 10.1016/j.neucom.2021.10.052]

Tan F X, Kong Y T, Fan Y Y, Liu F, Zhou D X, Zhang H, Chen L, Gao L and Qian Y R. 2021. SDNet: mutil-branch for single image deraining using swin[EB/OL]. [2021-05-31] . https://arxiv.53yu.com/pdf/2105.15077.pdf https://arxiv.53yu.com/pdf/2105.15077.pdf

Tremblay M, Halder S S, De Charette R and Lalonde J F. 2021. Rain rendering for evaluating and improving robustness to bad weather. International Journal of Computer Vision, 129(2): 341-360[DOI: 10.1007/s11263-020-01366-3]

Venkatanath N, Praneeth D, Chandrasekhar M, Channappayya S S and Medasani S S. 2015. Blind image quality evaluation using perception based features//Proceedings of the 21st National Conference on Communications (NCC). Mumbai, India: IEEE: 1-6[ DOI: 10.1109/NCC.2015.7084843 http://dx.doi.org/10.1109/NCC.2015.7084843 ]

Vu D T, Gonzalez J L and Kim M. 2021. Exploiting global and local attentions for heavy rain removal on single images[EB/OL]. [2021-04-16] . https://arxiv.53yu.com/pdf/2104.08126.pdf https://arxiv.53yu.com/pdf/2104.08126.pdf

Wang C, Wang H Y, Su Z X and Yang Y. 2019a. Embedding non-local mean in squeeze-and-excitation network for single image deraining//Proceedings of 2019 IEEE International Conference on Multimedia and Expo Workshops. Shanghai, China: IEEE: 264-269[ DOI: 10.1109/ICMEW.2019.00-76 http://dx.doi.org/10.1109/ICMEW.2019.00-76 ]

Wang C, Wu Y T, Su Z X and Chen J Y. 2020a. Joint self-attention and scale-aggregation for self-calibrated deraining network//Proceedings of the 28th ACM International Conference on Multimedia. Seattle, USA: ACM: 2517-2525[ DOI: 10.1145/3394171.3413559 http://dx.doi.org/10.1145/3394171.3413559 ]

Wang C, Xing X Y, Wu Y T, Su Z X and Chen J Y. 2020b. DCSFN: deep cross-scale fusion network for single image rain removal//Proceedings of the 28th ACM International Conference on Multimedia. Seattle, USA: ACM: 1643-1651[ DOI: 10.1145/3394171.3413820 http://dx.doi.org/10.1145/3394171.3413820 ]

Wang G Q, Sun C M and Sowmya A. 2021a. Context-enhanced representation learning for single image deraining. International Journal of Computer Vision, 129(5): 1650-1674[DOI: 10.1007/s11263-020-01425-9]

Wang H, Wu Y C, Li M H, Zhao Q and Meng D Y. 2019b. Survey on rain removal from video and single image. SCIENCE CHINA Information Sciences[EB/OL]. [2021-11-01] . https://arxiv.53yu.com/pdf/1909.08326.pdf https://arxiv.53yu.com/pdf/1909.08326.pdf

Wang H, Wu Y C, Xie Q, Zhao Q, Liang Y, Zhang S J and Meng D Y. 2021b. Structural residual learning for single image rain removal. Knowledge-Based Systems, 213: #106595[DOI: 10.1016/j.knosys.2020.106595]

Wang H, Xie Q, Wu Y C, Zhao Q and Meng D Y. 2020c. Single image rain streaks removal: a review and an exploration. International Journal of Machine Learning and Cybernetics, 11(4): 853-872[DOI: 10.1007/s13042-020-01061-2]

Wang H, Xie Q, Zhao Q and Meng D Y. 2020d. A model-driven deep neural network for single image rain removal//Proceedings of 2020 IEEE /CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 3100-3109[ DOI: 10.1109/CVPR42600.2020.00317 http://dx.doi.org/10.1109/CVPR42600.2020.00317 ]

Wang H, Yue Z S, Xie Q, Zhao Q, Zheng Y F and Meng D Y. 2021c. From rain generation to rain removal//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 14786-14796[ DOI: 10.1109/CVPR46437.2021.01455 http://dx.doi.org/10.1109/CVPR46437.2021.01455 ]

Wang M H, He H J and Li C. 2020. Single image rain removal based on selective kernel convolution using a residual refine factor. Journal of Image and Graphics, 25(12): 2484-2493

王美华, 何海君, 李超. 2020. 自适应卷积的残差修正单幅图像去雨. 中国图象图形学报, 25(12): 2484-2493)[DOI: 10.11834/jig.190682]

Wang T Y, Yang X, Xu K, Chen S, Zhang Q and Lau R W H. 2019c. Spatial attentive single-image deraining with a high quality real rain dataset//Proceedings of 2019 IEEE /CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 12262-12271[ DOI: 10.1109/CVPR.2019.01255 http://dx.doi.org/10.1109/CVPR.2019.01255 ]

Wang X F, Chen J, Jiang K, Han Z, Ruan W J, Wang Z Y and Liang C. 2020e. Single image de-raining via clique recursive feedback mechanism. Neurocomputing, 417: 142-154[DOI: 10.1016/j.neucom.2020.07.083]

Wang Y L, Gong D, Yang J, Shi Q F, Van Den Hengel A, Xie D H and Zeng B. 2020f. Deep single image deraining via modeling haze-like effect. IEEE Transactions on Multimedia, 23: 2481-2492[DOI: 10.1109/tmm.2020.3013383]

Wang Y L, Ma C and Zeng B. 2021d. Multi-decoding deraining network and quasi-sparsity based training//Proceedings of 2021 IEEE /CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 13370-13379

Wang Y L, Song Y B, Ma C and Zeng B. 2020g. Rethinking image deraining via rain streaks and vapors//Proceedings of the 16th European Conference on Computer Vision. Glasgow, USA: Springer: 367-382[ DOI: 10.1007/978-3-030-58520-4_22 http://dx.doi.org/10.1007/978-3-030-58520-4_22 ]

Wang Z, Bovik A C, Sheikh H R and Simoncelli E P. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4): 600-612[DOI: 10.1109/TIP.2003.819861]

Wang Z, Li J W and Song G. 2020h. DTDN: dual-task de-raining network//Proceedings of the 27th ACM International Conference on Multimedia. Nice, France: ACM: 1833-1841[ DOI: 10.1145/3343031.3350945 http://dx.doi.org/10.1145/3343031.3350945 ]

Wang Z D, Cun X D, Bao J M, Zhou W G, Liu J Z and Li H Q. 2021e. Uformer: a general U-shaped transformer for image restoration[EB/OL]. [2021-11-15] . https://arviv.org/pdf/2106.03106.pdf https://arviv.org/pdf/2106.03106.pdf

Wang Z Y, Chang S Y, Yang Y Z, Liu D and Huang T S. 2016. Studying very low resolution recognition using deep networks//Proceedings of2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 4792-4800[ DOI: 10.1109/CVPR.2016.518 http://dx.doi.org/10.1109/CVPR.2016.518 ]

Wei W, Meng D Y, Zhao Q, Xu Z B and Wu Y. 2019a. Semi-supervised transfer learning for image rain removal//Proceedings of 2019 IEEE /CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 3872-3881[ DOI: 10.1109/CVPR.2019.00400 http://dx.doi.org/10.1109/CVPR.2019.00400 ]

Wei Y Y, Zhang Z, Wang Y, Xu M L, Yang Y, Yan S C and Wang M. 2021a. DerainCycleGAN: rain attentive CycleGAN for single image deraining and rainmaking. IEEE Transactions on Image Processing, 30: 4788-4801[DOI: 10.1109/TIP.2021.3074804]

Wei Y Y, Zhang Z, Wang Y, Zhang H J, Zhao M B, Xu M L and Wang M. 2021b. Semi-deraingan: a new semi-supervised single image deraining//Proceedings of 2021 IEEE International Conference on Multimedia and Expo (ICME). Shenzhen, China: IEEE: 1-6[ DOI: 10.1109/ICME51207.2021.9428285 http://dx.doi.org/10.1109/ICME51207.2021.9428285 ]

Wei Y Y, Zhang Z, Zhang H J, Hong R C and Wang M. 2019b. A coarse-to-fine multi-stream hybrid deraining network for single image deraining//Proceedings of 2019 IEEE International Conference on Data Mining. Beijing, China: IEEE: 628-637[ DOI: 10.1109/ICDM.2019.00073 http://dx.doi.org/10.1109/ICDM.2019.00073 ]

Xie Q Q, Zhang H and Gai S. 2022. Multi-resolution context aggregation network for single image rain removal. Journal of Computer-Aided Design and Computer Graphics, 34(2): 232-244

谢强强, 张海, 盖杉. 2022. 多分辨率上下文聚合网络的单幅图像去雨方法. 计算机辅助设计与图形学学报, 34(2): 232-244)[DOI: 10.3724/SP.J.1089.2022.18887]

Xue P and He H. 2021. Research of single image rain removal algorithm based on LBP-CGAN rain generation method. Mathematical Problems in Engineering, 2021: #8865843[DOI: 10.1155/2021/8865843]

Yang W H, Liu J Y, Yang S and Guo Z M. 2019a. Scale-free single image deraining via visibility-enhanced recurrent wavelet learning. IEEE Transactions on Image Processing, 28(6): 2948-2961[DOI: 10.1109/TIP.2019.2892685]

Yang W H, Tan R T, Feng J S, Guo Z M, Yan S C and Liu J Y. 2020a. Joint rain detection and removal from a single image with contextualized deep networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(6): 1377-1393[DOI: 10.1109/TPAMI.2019.2895793]

Yang W H, Tan R T, Feng J S, Liu J Y, Guo Z M and Yan S C. 2017. Deep joint rain detection and removal from a single image//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 1685-1694[ DOI: 10.1109/CVPR.2017.183 http://dx.doi.org/10.1109/CVPR.2017.183 ]

Yang W H, Tan R T, Wang S Q, Fang Y M and Liu J Y. 2021. Single image deraining: from model-based to data-driven and beyond. IEEE Transactions on PatternAnalysis and Machine Intelligence, 43(11): 4059-4077[DOI: 10.1109/TPAMI.2020.2995190]

Yang Y Z and Lu H. 2019b. Single image deraining using a recurrent multi-scale aggregation and enhancement network//Proceedings of 2019 IEEE International Conference on Multimedia and Expo. Shanghai, China: IEEE: 1378-1383[ DOI: 10.1109/ICME.2019.00239 http://dx.doi.org/10.1109/ICME.2019.00239 ]

Yang Y Z and Lu H. 2019c. Single image deraining via recurrent hierarchy enhancement network//Proceedings of the 27th ACM International Conference on Multimedia. Nice, France: ACM: 1814-1822[ DOI: 10.1145/3343031.3351149 http://dx.doi.org/10.1145/3343031.3351149 ]

Yang Y Z, Ran W and Lu H. 2020b. Rddan: a residual dense dilated aggregated network for single image deraining//Proceedings of 2020 IEEE International Conference on Multimedia and Expo (ICME). London, UK: IEEE: 1-6[ DOI: 10.1109/ICME46284.2020.9102945 http://dx.doi.org/10.1109/ICME46284.2020.9102945 ]

Yasarla R and Patel V M. 2019. Uncertainty guided multi-scale residual learning-using a cycle spinning CNN for single image de-raining//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 8397-8406[ DOI: 10.1109/CVPR.2019.00860 http://dx.doi.org/10.1109/CVPR.2019.00860 ]

Yasarla R and Patel V M. 2020. Confidence measure guided single image de-raining. IEEE Transactions on Image Processing, 29: 4544-4555[DOI: 10.1109/TIP.2020.2973802]

Yasarla R, Sindagi V A and Patel V M. 2020. Syn2Real transfer learning for image deraining using gaussian processes//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 2723-2733[ DOI: 10.1109/CVPR42600.2020.00280 http://dx.doi.org/10.1109/CVPR42600.2020.00280 ]

Ye Y T, Chang Y, Zhou H Y and Yan L X. 2021. Closing the loop: joint rain generation and removal via disentangled image translation//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 2053-2062[ DOI: 10.1109/CVPR46437.2021.00209 http://dx.doi.org/10.1109/CVPR46437.2021.00209 ]

Yu W J, Huang Z, Zhang W, Feng L T and Xiao N. 2019. Gradual network for single image de-raining//Proceedings of the 27th ACM International Conference on Multimedia. Nice, France: ACM: 1795-1804[ DOI: 10.1145/3343031.3350883 http://dx.doi.org/10.1145/3343031.3350883 ]

Zhang H and Patel V M. 2018. Density-aware single image de-raining using a multi-stream dense network//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 695-704[ DOI: 10.1109/CVPR.2018.00079 http://dx.doi.org/10.1109/CVPR.2018.00079 ]

Zhang H, Sindagi V and Patel V M. 2020a. Image de-raining using a conditional generative adversarial network. IEEE Transactions on Circuits and Systems for Video Technology, 30(11): 3943-3956[DOI: 10.1109/TCSVT.2019.2920407]

Zhang K H, Li D X, Luo W H and Ren W Q. 2021a. Dual attention-in-attention model for joint rain streak and raindrop removal. IEEE Transactions on Image Processing, 30: 7608-7619[DOI: 10.1109/TIP.2021.3108019]

Zhang K H, Luo W H, Yu Y J, Ren W Q, Zhao F, Li C S, Ma L, Liu W and Li H D. 2021b. Beyond monocular deraining: parallel stereo deraining network via semantic prior[EB/OL]. [2021-05-09] . https://arxiv.53yu.com/pdf/2105.03830.pdf https://arxiv.53yu.com/pdf/2105.03830.pdf

Zhang L, Zhang L and Bovik A C. 2015. A feature-enriched completely blind image quality evaluator. IEEE Transactions on Image Processing, 24(8): 2579-2591

Zhang W X, Li D Q, Ma C, Zhai G T, Yang X K and Ma K D. 2021c. Continual learning for blind image quality assessment[EB/OL]. [2021-02-19] . https://arxiv.53yu.com/pdf/2102.09717.pdf https://arxiv.53yu.com/pdf/2102.09717.pdf

Zhang W X, Ma K D, Yan J, Deng D X and Wang Z. 2020b. Blind image quality assessment using a deep bilinear convolutional neural network. IEEE Transactions on Circuits and Systems for Video Technology, 30(1): 36-47[DOI: 10.1109/TCSVT.2018.2886771]

Zhang W X, Ma K D, Zhai G T and Yang X K. 2021 d. Task-specific normalization for continual learning of blind image quality models[EB/OL]. [2021-07-28] . https://arxiv.53yu.com/pdf/2107.13429.pdf https://arxiv.53yu.com/pdf/2107.13429.pdf

Zhang X F and Li J J. 2021. Single image de-raining using a recurrent dual-attention-residual ensemble network. Journal of Software, 32(10): 3283-3292

张学锋, 李金晶. 2021. 基于双注意力残差循环单幅图像去雨集成网络. 软件学报, 32(10): 3283-3292)[DOI: 10.13328/j.cnki.jos.006018]

Zhang Z, Wei Y Y, Zhang H J, Yang Y, Yan S C and Wang M. 2021e. Data-driven single image deraining: a comprehensive review and new perspectives. TechRxiv Preprint

Zhao H S, Shi J P, Qi X J, Wang X G and Jia J Y. 2017. Pyramid scene parsing network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 6230-6239[ DOI: 10.1109/CVPR.2017.660 http://dx.doi.org/10.1109/CVPR.2017.660 ]

Zheng Y P, Yu X, Liu M M and Zhang S L. 2019. Residual multiscale based single image deraining//Proceedings of the 30th British Machine Vision Conference 2019. Cardiff, UK: BMVC: 147

Zheng Y P, Yu X, Liu M M and Zhang S L. 2022. Single-image deraining via recurrent residual multiscale networks. IEEE Transactions on Neural Networks and Learning Systems, 33(3): 1310-1323[DOI: 10.1109/TNNLS.2020.3041752]

Zhu H D, Wang C, Zhang Y J, Su Z X and Zhao G H. 2020. Physical model guided deep image deraining//Proceedings of 2020 IEEE International Conference on Multimedia and Expo (ICME). London, UK: IEEE: 1-6[ DOI: 10.1109/ICME46284.2020.9102878 http://dx.doi.org/10.1109/ICME46284.2020.9102878 ]

Zhu H Y, Peng X, Zhou J T, Yang S F, Chanderasekh V, Li L Y and Lim J H. 2019. Singe image rain removal with unpaired information: a differentiable programming perspective. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1): 9332-9339[DOI: 10.1609/aaai.v33i01.33019332]