多尺度低秩图像盲去模糊方法

周志豪; 张玉龙; 唐启凡; 闫金涛

doi:10.7652/xjtuxb202109019

您当前的位置：

首页 >

文章列表页 >

多尺度低秩图像盲去模糊方法

更新时间：2025-07-09

- 多尺度低秩图像盲去模糊方法
- Multi-Scale Low-Rank Blind Image Deblurring Method
- 西安交通大学学报 2021年55卷第9期页码：168-177
- 作者机构：
  
  西安交通大学软件学院,西安,710049
- 作者简介：
- 基金信息：
  
  : 2021-03-30。作者简介: 周志豪(1997—),男,硕士生:张玉龙(通信作者),男,讲师。基金项目: 国家自然科学基金资助项目(61573273)
- DOI：10.7652/xjtuxb202109019
  中图分类号： TP391
- 网络首发：2021-09-10，
  
  纸质出版：2021
- 稿件说明：
移动端阅览
周志豪, 张玉龙, 唐启凡, 等. 多尺度低秩图像盲去模糊方法[J]. 西安交通大学学报, 2021,55(9):168-177.

Multi-Scale Low-Rank Blind Image Deblurring Method[J]. 2021, 55(9): 168-177.
周志豪, 张玉龙, 唐启凡, 等. 多尺度低秩图像盲去模糊方法[J]. 西安交通大学学报, 2021,55(9):168-177. DOI： 10.7652/xjtuxb202109019.

Multi-Scale Low-Rank Blind Image Deblurring Method[J]. 2021, 55(9): 168-177. DOI： 10.7652/xjtuxb202109019.

摘要

针对现有的大多数基于统计先验的单幅图像盲去模糊方法对图像纹理细节恢复效果不佳且存在振铃效应的问题

提出了一种基于逐块局部最大梯度先验和低秩先验的多尺度图像盲去模糊方法。为了恢复得到清晰图像

采用由粗到精的多尺度框架

通过灰度化与下采样操作逐层构建图像金字塔; 在单尺度层面

将逐块局部最大梯度先验和低秩先验带入到最大后验概率框架中

利用交替方向乘子法与半二次分裂法估计出潜在图像和模糊核; 结合超拉普拉斯先验与总变差L

方法

对模糊图像与估得的模糊核进行非盲反卷积

获得清晰图像。在计算过程中

由于直接求解低秩项的计算代价很大

将加权Schatte-1/2范数约束的低秩项子问题转化为非凸权重L

1/2

范数子问题

采用广义软阈值方法求得全局最优解。在基准数据集上的实验结果表明:与现有的经典图像去模糊方法相比

所提方法取得了更优的图像去模糊效果; 在Köhler的合成数据集上进行图像去模糊后

平均峰值信噪比为30.06 dB

平均结构相似性为0.946 5

估计出的模糊核更加精确。

Abstract

Most existing single image blind deblurring methods based on statistical priors suffer a poor texture restoration and ringing artifacts. A multi-scale blind image deblurring method based on patch-wise local maximum gradient prior and low rank prior is proposed in this paper. Specifically

we choose a coarse-to-fine multi-scale framework to construct an image pyramid via gray-scale and down-sampling operations layer by layer. At the single-scale level

the patch-wise local maximum gradient prior and the low-rank prior are put into the MAP framework

and then both the intermediate latent image and blur kernel are estimated with the alternating direction method of multiplier and the half-quadr

atic splitting method. We finally obtain the sharp image by performing non-blind deconvolution for the blurred image and estimated kernel based on hyper-Laplacian prior and total variation-L

method. Solving the low-rank regularization directly is computationally expensive

we thus transform the sub-problem of low-rank regularization term constrained by weighted Schatte-1/2 norm into a sub-problem of non-convex weighted L

1/2

-norm

and then adopt the generalized soft-thresholding method(GST)to achieve the global optimal solution. Experimental results and comparisons with the existing classical image deblurring methods on the benchmark datasets show that the proposed method facilitates a better image deblurring performance. After image deblurring on Köhler synthetic dataset

the average peak signal-to-noise ratio reaches 30.06 dB

the average structural similarity reaches 0.946 5

and the estimated blur kernel gets more accurate.

关键词

Keywords

references

黄正源, 谢维成, 黄化入, 等. 图像运动模糊还原技术综述 [J]. 计算机工程与应用, 2020, 56(24): 28-34.

HUANG Zhengyuan, XIE Weicheng, HUANG Huaru, et al. Overview of motion deblurring techniques for images [J]. Computer Engineering and Applications, 2020, 56(24): 28-34.

王杨, 张鑫, 许闪闪, 等. 基于维纳滤波器和生成对抗网络的动态模糊图像处理方法 [J]. 计算机系统应用, 2019, 28(4): 145-150.

WANG Yang, ZHANG Xin, XU Shanshan, et al. Dynamic fuzzy image processing based on Wiener filter and generative adversarial networks [J]. Computer Systems Applications, 2019, 28(4): 145-150.

张建国, 拓洋洋, 蒋瑞娇, 等. Richardson-Lucy算法在模糊图像复原中的改进 [J]. 计量学报, 2020, 41(2): 153-158.

ZHANG Jianguo, TA Yangyang, JIANG Ruijiao, et al. Improvement of the Richardson-Lucy algorithm in blurred image restoration [J]. Acta Metrologica Sinica, 2020, 41(2): 153-158.

ZHUANG Peixian, DING Xinghao, DUAN Jinming. Subspace-based non-blind deconvolution [J]. Mathematical Biosciences and Engineering, 2019, 16(4): 2202-2218.

MICHAELI T, IRANI M. Blind deblurring using internal patch recurrence [C]∥Proceedings of the 13th European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2014: 783-798.

XU Li, ZHENG Shicheng, JIA Jiaya. Unnatural L0 sparse representation for natural image deblurring [C]∥Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2013: 1107-1114.

LAI Weisheng, DING Jian-jiun, LIN Yenyu, et al. Blur kernel estimation using normalized color-line priors [C]∥Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2015: 64-72.

LIU Jun, YAN Ming, ZENG Tieyong. Surface-aware blind image deblurring [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(3): 1041-1055.

PAN Jinshan, SUN Deqing, PFISTER H, et al. Blind image deblurring using dark channel prior [C]∥Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2016: 1628-1636.

YAN Yanyang, REN Wenqi, GUO Yuanfang, et al. Image deblurring via extreme channels prior [C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2017: 6978-6986.

WEN Fei, YING Rendong, LIU Yipeng, et al. A simple local minimal intensity prior and an improved algorithm for blind image deblurring [J/OL]. IEEE Transactions on Circuits and Systems for Video Technology[2021-02-01]. https:∥ieeexplore.ieee.org/stamp/stamp.jsp?tp=arnumber=9241002.

黄文君, 李杰, 齐春. 低秩与字典表达分解的浓雾霾场景图像去雾算法 [J]. 西安交通大学学报, 2020, 54(4): 118-125.

HUANG Wenjun, LI Jie, QI Chun. A defogging algorithm for dense fog images via low-rank and dictionary expression decomposition [J]. Journal of Xi'an Jiaotong University, 2020, 54(4): 118-125.

彭天奇, 禹晶, 肖创柏. 基于跨尺度低秩约束的图像盲解卷积算法 [J/OL]. 自动化学报 [2021-02-01]. https:∥doi.org/10.16383/j.aas.c190845.

PENG Tianqi, YU Jing, XIAO Chuangbai. Blind image deconvolution via cross-scale low rank prior [J/OL]. Acta Automatica Sinica [2021-02-01]. https:∥doi.org/10.16383/j.aas.c190845.

REN Wenqi, ZHANG Jiawei, MA Lin, et al. Deep non-blind deconvolution via generalized low-rank approximation [J]. Advances in Neural Information Processing Systems, 2018, 31: 297-307.

CHEN Liang, FANG Faming, WANG Tingting, et al. Blind image deblurring with local maximum gradient prior [C]∥Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 1742-1750.

GU Shuhang, XIE Qi, MENG Deyu, et al. Weighted nuclear norm minimization and its applications to low level vision [J]. International Journal of Computer Vision, 2017, 121(2): 183-208.

XIE Yuan, GU Shuhang, LIU Yan, et al. Weighted Schatten p0 sparse representation for natural image deblurring [C]∥Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2013: 1107-1114.

LIU Jun, YAN Ming, ZENG Tieyong. Surface-aware blind image deblurring [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(3): 1041-1055.

黄文君, 李杰, 齐春. 低秩与字典表达分解的浓雾霾场景图像去雾算法 [J]. 西安交通大学学报, 2020, 54(4): 118-125.

HUANG Wenjun, LI Jie, QI Chun. A defogging algorithm for dense fog images via low-rank and dictionary expression decomposition [J]. Journal of Xi'an Jiaotong University, 2020, 54(4): 118-125.

彭天奇, 禹晶, 肖创柏. 基于跨尺度低秩约束的图像盲解卷积算法 [J/OL]. 自动化学报 [2021-02-01]. https:∥doi.org/10.16383/j.aas.c190845.

PENG Tianqi, YU Jing, XIAO Chuangbai. Blind image deconvolution via cross-scale low rank prior [J/OL]. Acta Automatica Sinica [2021-02-01]. https:∥doi.org/10.16383/j.aas.c190845.

REN Wenqi, ZHANG Jiawei, MA Lin, et al. Deep non-blind deconvolution via generalized low-rank approximation [J]. Advances in Neural Information Processing Systems, 2018, 31: 297-307.

GU Shuhang, XIE Qi, MENG Deyu, et al. Weighted nuclear norm minimization and its applications to low level vision [J]. International Journal of Computer Vision, 2017, 121(2): 183-208.

XIE Yuan, GU Shuhang, LIU Yan, et al. Weighted Schatten rm minimization for image denoising and background subtraction [J]. IEEE Transactions on Image Processing, 2016, 25(10): 4842-4857.

BAI Yuanchao, JIA Huizhu, JIANG Ming, et al. Single-image blind deblurring using multi-scale latent structure prior [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(7): 2033-2045.

ZUO Wangmeng, REN Dongwei, ZHANG D, et al. Learning iteration-wise generalized shrinkage-thresholding operators for blind deconvolution [J]. IEEE Transactions on Image Processing, 2016, 25(4): 1751-1764.

ZHANG Xinxin, WANG Ronggang, TIAN Yonghong, et al. Image deblurring using robust sparsity priors [C]∥Proceedings of the 2015 IEEE International Conference on Image Processing(ICIP). Piscataway, NJ, USA: IEEE, 2015: 138-142.

KÖHLER R, HIRSCH M, MOHLER B, et al. Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database [C]∥Proceedings of the 12th European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2012: 27-40.

LEVIN A, WEISS Y, DURAND F, et al. Understanding and evaluating blind deconvolution algorithms [C]∥Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2009: 1964-1971.

LAI Weisheng, HUANG Jiabin, HU Zhe, et al. A comparative study for single image blind deblurring [C]∥Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2016: 1701-1709.

CHO S, LEE S. Fast motion deblurring [J]. ACM Transactions on Graphics, 2009, 28(5): 1-8.

LIU Yuhang, DONG Wenyong, GONG Dong, et al. Deblurring natural image using super-Gaussian fields [C]∥Proceedings of the 15th European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2018: 467-484.

JIN Meiguang, ROTH S, FAVARO P. Normalized blind deconvolution [C]∥Proceedings of the 15th European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2018: 694-711.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

冷库水平空气幕热湿阻隔性能数值模拟研究

多工况下离心压气机叶轮-机匣一体联合设计优化

扇贝仿生密封腔室内超临界二氧化碳泄漏流湍动能耗散机理研究

EBSILON软件在热电联产系统优化中的应用综述

电子级超纯氮深冷空分流程节能优化研究