Single Image De-raining Based on Low-rank Matrix Completion

Zhu Jian; Liu Pei-yu; Chen Bing-feng; Cai Rui-chu

doi:10.12052/gdutxb.200023

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Single Image De-raining Based on Low-rank Matrix Completion

更新时间：2026-05-27

- Single Image De-raining Based on Low-rank Matrix Completion
- Vol. 37, Issue 4, Pages: 1-8(2020)
- 作者机构：
  
  广东工业大学计算机学院,广东,广州,510006
- 作者简介：
- 基金信息：
- DOI：10.12052/gdutxb.200023
  CLC： TP391
- Online First：11 July 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
朱鉴, 刘培钰, 陈炳丰, 蔡瑞初. 基于低秩矩阵补全的单幅图像去雨算法[J]. 广东工业大学学报, 2020, 37(4): 1-8.

Zhu Jian, Liu Pei-yu, Chen Bing-feng, et al. Single Image De-raining Based on Low-rank Matrix Completion[J]. 2020, 37(4): 1-8.
朱鉴, 刘培钰, 陈炳丰, 蔡瑞初. 基于低秩矩阵补全的单幅图像去雨算法[J]. 广东工业大学学报, 2020, 37(4): 1-8. DOI： 10.12052/gdutxb.200023.

Zhu Jian, Liu Pei-yu, Chen Bing-feng, et al. Single Image De-raining Based on Low-rank Matrix Completion[J]. 2020, 37(4): 1-8. DOI： 10.12052/gdutxb.200023.

摘要

提出一种基于低秩矩阵补全的单幅图像去雨算法

该算法采用检测、修补、优化的三阶段策略。在检测雨阶段

利用雨的亮度先验信息构建检测雨模型; 在修补阶段

先采用相似块匹配算法构造相似块矩阵

再利用其具有低秩属性的特点

将去雨问题转化为低秩矩阵补全问题; 在优化阶段

提出修正策略进一步提升去雨效果和客观度量值。在合成雨图和真实雨图上验证算法

实验结果表明

该算法表现出较好的去雨效果

且对大雨图像的处理也较为满意

相比其他方法在客观度量值和主观视觉上均有一定的优势。

Abstract

A single image de-raining algorithm based on low rank matrix completion is proposed. The algorithm adopts the three-stage strategy of detection

repair and optimization. In the rain detection stage

the rain intensity information is used as a prior to build a detection model. In the repair stage

a similar patch matching algorithm is first used to construct a similar patch matrix

and then the problem of de-raining is transformed into the task of low-rank matrix completion based on its low-rank attribute. In the optimization stage

a correction strategy is adopted to further improve the de-raining effect and objective measurements. The algorithm is verified on synthetic rain images and real rain images. Experimental results show that the algorithm shows a good rain removal effect

and the processing of heavy rain images is also satisfactory. Compared with other methods

it has certain advantages in both objective metrics and subjective visual quality.

关键词

Keywords

references

KIM J H, SIM J Y, KIM C S. Video deraining and desnowing using temporal correlation and low-rank matrix completion [J]. IEEE Transactions on Image Processing, 2015, 24(9): 2658-2670.

JIANG T X, HUANG T Z, ZHAO X L, et al. A novel tensor-based video rain streaks removal approach via utilizing discriminatively intrinsic priors[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 4057-4066.

LI M, XIE Q, ZHAO Q, et al. Video rain streak removal by multiscale convolutional sparse coding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6644-6653.

CHEN J, TAN C H, HOU J, et al. Robust video content alignment and compensation for rain removal in a cnn framework[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6286-6295.

XU J, ZHAO W, LIU P, et al. Removing rain and snow in a single image using guided filter[C]// Proceedings of the IEEE International Conference on Computer Science and Automation Engineering (CSAE). Zhangjiajie: IEEE, 2012, 2: 304-307.

ZHENG X, LIAO Y, GUO W, et al. Single-image-based rain and snow removal using multi-guided filter[C]//Proceedings of the International Conference on Neural Information Processing. Berlin: Springer, 2013: 258-265.

KANG L W, LIN C W, FU Y H. Automatic single-image-based rain streaks removal via image decomposition [J]. IEEE Transactions on Image Processing, 2011, 21(4): 1742-1755.

LI Y, TAN R T, GUO X, et al. Rain streak removal using layer priors[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2736-2744.

LUO Y, XU Y, JI H. Removing rain from a single image via discriminative sparse coding[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 3397-3405.

ZHU L, FU C W, LISCHINSKI D, et al. Joint bi-layer optimization for single-image rain streak removal[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2526-2534.

LIU R, JIANG Z, FAN X, et al . Knowledge-driven deep unrolling for robust image layer separation [J ] . IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(5): 1653-1666.

FU X, HUANG J, DING X, et al . Clearing the skies: A deep network architecture for single-image rain removal [J ] . IEEE Transactions on Image Processing, 2017, 26(6): 2944-2956.

FU X, HUANG J, ZENG D, et al. Removing rain from single images via a deep detail network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 3855-3863.

XIANG P, WANG L, WU F, et al . Single-image de-raining with feature-supervised generative adversarial network [J ] . IEEE Signal Processing Letters, 2019, 26(5): 650-654.

YANG W, TAN R T, FENG J, et al . Joint rain detection and removal from a single image with contextualized deep networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.

ZHANG H, PATEL V M. Density-aware single image de-raining using a multi-stream dense network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 695-704.

FU X Y, SUN Q, HUANG Y, et al . Method for single image de-raining based on deep adjacently connected networks [J ] . Computer Science, 2020, 47(2): 106-111.

SHI J R, ZHENG X Y, WEI Z T, et al . Survey on algorithms of low-rank matrix recovery [J ] . Application Research of Computers, 2013, 30(6): 1601-1605.

LU C, LIN Z, YAN S. Smoothed low rank and sparse matrix recovery by iteratively reweighted least squares minimization [J]. IEEE Transactions on Image Processing, 2014, 24(2): 646-654.

MA S, GOLDFARB D, CHEN L. Fixed point and Bregman iterative methods for matrix rank minimization [J]. Mathematical Programming, 2011, 128(1-2): 321-353.

LU C, TANG J, YAN S, et al. Generalized nonconvex nonsmooth low-rank minimization[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 4130-4137.

DONG W, SHI G, LI X. Nonlocal image restoration with bilateral variance estimation: a low-rank approach [J]. IEEE Transactions on Image Processing, 2012, 22(2): 700-711.

JI H, LIU C, SHEN Z, et al. Robust video denoising using low rank matrix completion[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 1791-1798.

WEN F, CHU L, LIU P, et al . A survey on nonconvex regularization-based sparse and low-rank recovery in signal processing, statistics, and machine learning [J ] . IEEE Access, 2018, 6: 69883-69906.

WANG Y, HUANG T Z. A tensor-based low-rank model for single-image rain streaks Removal [J]. IEEE Access, 2019, 7: 83437-83448.

ABDEL-HAKIM A E. A novel approach for rain removal from videos using low-rank recovery[C]//20145th International Conference on Intelligent Systems, Modelling and Simulation. Langkawi: IEEE, 2014: 351-356.

ZHANG H, PATEL V M. Convolutional sparse and low-rank coding-based rain streak removal[C]//2017 IEEE Winter Conference on Applications of Computer Vision (WACV). Santa Rosa: IEEE, 2017: 1259-1267.

CANDES E J, PLAN Y. Matrix completion with noise [J]. Proceedings of the IEEE, 2010, 98(6): 925-936.

HORE A, ZIOU D. Image quality metrics: PSNR vs. SSIM[C]//201020th International Conference on Pattern Recognition. Istanbul: IEEE, 2010: 2366-2369.

LI H L, LING J, XU S Q. The exegesis of the quality assessment PSNR of images [J]. Journal of Guangdong University of Technology, 2004, 21(3): 74-78.

YANG W, TAN R T, FENG J, et al. Deep joint rain detection and removal from a single image[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 1357-1366.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Energy Management Strategy of Hybrid Locomotive Based on Road Condition Parameters

Research and Implementation of a Pulsed Laser Ranging Method Based on Digital Mixing

SCA-YOLO: Real-time Target Detection Based on Deformable Convolution and Context-aware Attention

A Resource Allocation Optimization Method for Multi-UAV Integrated Sensing, Computing, and Communication Towards Disaster Relief

The Cross-twin Physics-informed Neural Network for Wave Equations with Conserved Quantities

Related Author

No data

Related Institution

No data

AI问答

⁰