Blind Single-Image Super-Resolution Algorithm Based on Cross-Scale Low Rank Prior

ZHOU Xiao-yan; QIN Hong-wu; YU Jing; FENG Wen-jing

doi:10.12263/DZXB.20220150

您当前的位置：

首页 >

文章列表页 >

Blind Single-Image Super-Resolution Algorithm Based on Cross-Scale Low Rank Prior

PAPERS | 更新时间：2026-04-10

- Blind Single-Image Super-Resolution Algorithm Based on Cross-Scale Low Rank Prior
- ACTA ELECTRONICA SINICA Vol. 52, Issue 1, Pages: 338-353(2024)
- 作者机构：
  
  1.西北师范大学计算机科学与工程学院，甘肃兰州 730000
  2.北京工业大学信息学部，北京 100124
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20220150
  CLC： TP391.41;
- Received：07 February 2022，
  
  Revised：2022-05-05，
  
  Published：25 January 2024
- 稿件说明：
移动端阅览
周晓燕,秦红武,禹晶等.基于跨尺度低秩约束的单幅图像盲超分辨率算法[J].电子学报,2024,52(01):338-353.

ZHOU Xiao-yan,QIN Hong-wu,YU Jing,et al.Blind Single-Image Super-Resolution Algorithm Based on Cross-Scale Low Rank Prior[J].ACTA ELECTRONICA SINICA,2024,52(01):338-353.
周晓燕,秦红武,禹晶等.基于跨尺度低秩约束的单幅图像盲超分辨率算法[J].电子学报,2024,52(01):338-353. DOI： 10.12263/DZXB.20220150.

ZHOU Xiao-yan,QIN Hong-wu,YU Jing,et al.Blind Single-Image Super-Resolution Algorithm Based on Cross-Scale Low Rank Prior[J].ACTA ELECTRONICA SINICA,2024,52(01):338-353. DOI： 10.12263/DZXB.20220150.

摘要

单幅图像盲超分辨率方法是在模糊核未知的情况下仅利用单幅低分辨率图像重建高分辨率图像，这是一个严重的欠定逆问题.超分辨率正则化方法通过正则化约束项引入附加信息，为低分辨率图像恢复或重建合理的高频成分.本文将跨尺度自相似性与低秩先验相结合，提出了一种基于跨尺度低秩约束的单幅图像盲超分辨率方法，采用联合建模的方法同时估计模糊核与高分辨率图像.利用高分辨率图像、低分辨率图像及其降采样图像之间的跨尺度自相似性，对于低分辨率图像中的图像块在降采样图像中搜索相似块，将该图像块在高分辨率重建图像中对应的父块与其相似块在低分辨率图像中对应的父块合并，构造跨尺度相似图像块组矩阵.由于低分辨率图像中的跨尺度相似图像块能够为重建图像块提供潜在的细节信息，因此对相似图像块组矩阵进行低秩约束，在迭代求解过程中迫使重建图像恢复高频成分，进而促使模糊核的估计更加准确.此外，低秩约束能够表示数据的全局结构，对噪声具有鲁棒性.在真实和模拟图像上的实验表明，本文的算法能够准确地估计模糊核，重建高分辨率图像的边缘和细节，优于现有的自监督盲超分辨率算法.

Abstract

Blind single-image super-resolution refers to reconstructing the high-resolution image from a single low-resolution one with an unknown blur kernel

which is a severely ill-posed inverse problem. The additional information about the latent high-resolution image can be incorporated by adding the regularizer in order to recover or reconstruct reasonable high-frequency details for the low-resolution image. In this paper

we propose a blind super-resolution method based on the cross-scale low rank prior from a single low-resolution image

which alternates between updating the blur kernel and the high-resolution image by a jointly modeling approach. According to the self-similarity across the high-resolution image

the low-resolution image and its down-sampled image

we search for similar patches from the down-sampled image for the low-resolution patch

and group into a matrix the cross-scale similar image patches consisting of the parents of the low-resolution patch and its similar patches in the high-resolution reconstructed image and the low-resolution image respectively. Since the cross-scale similar patches in the low-resolution image provide potential details for reconstructing the high-resolution image patches

the low rank matrix approximation applied to the cross-scale similar patches enforces the reconstructed image to recover more high-frequency details and thus promotes the accuracy of the kernel estimation during the iteration. In addition

the low rank regularization elegantly indicates the non-local structure of data inherently robust to noise. Experimental results on real and simulated images show that the proposed method can accurately estimate the blur kernel and reconstruct high-resolution image with sharp edges and fine details

which outperforms the existing blind super-resolution methods based on unsupervised learning.

关键词

Keywords

references

MICHAELI T , IRANI M . Nonparametric blind super-resolution [C]// 2013 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2014 : 945 - 952 .

ZHAO X L , WU Y D , TIAN J S , et al . Single image super-resolution via blind blurring estimation and anchored space mapping [J]. Computational Visual Media , 2016 , 2 ( 1 ): 71 - 85 .

HE Y , YAP K H , CHEN L , et al . A soft MAP framework for blind super-resolution image reconstruction [J]. Image and Vision Computing , 2009 , 27 ( 4 ): 364 - 373 .

GU J J , LU H N , ZUO W M , et al . Blind super-resolution with iterative kernel correction [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 1604 - 1613 .

LUO Z X , HUANG Y , LI S , et al . Unfolding the alternating optimization for blind super resolution [EB/OL]. ( 2020-10-06 )[ 2022-02-07 ]. https://arxiv.org/abs/2010.02631 https://arxiv.org/abs/2010.02631 .

WANG W , ZHANG H C , YUAN Z H , et al . Unsupervised real-world super-resolution: A domain adaptation perspective [C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2022 : 4298 - 4307 .

WEI Y X , GU S H , LI Y W , et al . Unsupervised real-world image super resolution via domain-distance aware training [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 13380 - 13389 .

BELL-KLIGLER S , SHOCHER A , IRANI M . Blind super-resolution kernel estimation using an internal-GAN [EB/OL]. ( 2019-09-14 )[ 2022-02-07 ]. https://arxiv.org/abs/1909.06581 https://arxiv.org/abs/1909.06581 .

GLASNER D , BAGON S , IRANI M . Super-resolution from a single image [C]// 2009 IEEE 12th International Conference on Computer Vision . Piscataway : IEEE , 2010 : 349 - 356 .

潘宗序 , 禹晶 , 胡少兴 , 等 . 基于多尺度结构自相似性的单幅图像超分辨率算法 [J]. 自动化学报 , 2014 , 40 ( 4 ): 594 - 603 .

PAN Z X , YU J , HU S X , et al . Single image super resolution based on multi-scale structural self-similarity [J]. Acta Automatica Sinica , 2014 , 40 ( 4 ): 594 - 603 . (in Chinese)

潘宗序 , 禹晶 , 肖创柏 , 等 . 基于多尺度非局部约束的单幅图像超分辨率算法 [J]. 自动化学报 , 2014 , 40 ( 10 ): 2233 - 2244 .

PAN Z X , YU J , XIAO C B , et al . Single-image super-resolution algorithm based on multi-scale nonlocal regularization [J]. Acta Automatica Sinica , 2014 , 40 ( 10 ): 2233 - 2244 . (in Chinese)

HUANG J B , SINGH A , AHUJA N . Single image super-resolution from transformed self-exemplars [C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2015 : 5197 - 5206 .

MEI Y Q , FAN Y C , ZHOU Y Q , et al . Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 5689 - 5698 .

SHOCHER A , COHEN N , IRANI M . Zero-shot super-resolution using deep internal learning [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3118 - 3126 .

CHEN X X , QI C . Low-rank neighbor embedding for single image super-resolution [J]. IEEE Signal Processing Letters , 2014 , 21 ( 1 ): 79 - 82 .

SHI J H , QI C . Low-rank sparse representation for single image super-resolution via self-similarity learning [C]// 2016 IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2016 : 1424 - 1428 .

WANG S , YUE B , LIANG X F , et al . How does the low-rank matrix decomposition help internal and external learnings for super-resolution [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 3 ): 1086 - 1099 .

YOU X G , XUE W Y , LEI J J , et al . Single image super-resolution with non-local balanced low-rank matrix restoration [C]// 2016 23rd International Conference on Pattern Recognition (ICPR) . Piscataway : IEEE , 2017 : 1255 - 1260 .

ZHAO N N , WEI Q , BASARAB A , et al . Fast single image super-resolution using a new analytical solution for l2-l2 problems [J]. IEEE Transactions on Image Processing , 2016 , 25 ( 8 ): 3683 - 3697 .

CAI J F , CANDÈS E J , SHEN Z W . A singular value thresholding algorithm for matrix completion [J]. SIAM Journal on Optimization , 2010 , 20 ( 4 ): 1956 - 1982 .

GU S H , ZHANG L , ZUO W M , et al . Weighted nuclear norm minimization with application to image denoising [C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2014 : 2862 - 2869 .

FRIEDMAN J H , BENTLEY J L , FINKEL R A . An algorithm for finding best matches in logarithmic expected time [J]. ACM Transactions on Mathematical Software , 1977 , 3 ( 3 ): 209 - 226 .

AGUSTSSON E , TIMOFTE R . NTIRE 2017 challenge on single image super-resolution: Dataset and study [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway : IEEE , 2017 : 1122 - 1131 .

LEDIG C , THEIS L , HUSZÁR F , et al . Photo-realistic single image super-resolution using a generative adversarial network [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 105 - 114 .

GUO Y , CHEN J , WANG J D , et al . Closed-loop matters: Dual regression networks for single image super-resolution [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 5406 - 5415 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image Mixed Denoising Using Quaternion-Based Non-Local Low Rank and Total Variation

A SVM-Based Blind Super-Resolution Image Restoration Algorithm

Study on Intelligent Burst Assembly Mechanism in Optical Burst Switch Networks

Related Author

LI Xiao-yao

WANG Lian-hong

ZHOU Yi-cong

ZHANG Jing

QIAO Jian-ping

LIU Ju

LI Yan-jun

HONG Xiao-bin

Related Institution

College of Electrical and Information Engineering, Hunan University

Department of Computer and Information Science, University of Macau, Macau

School of Information Science and Engineering,Shandong University

.of Optical fiber Communications,Beijing University of Posts and Telecommunications,Beijing

Beijing Northen Fiberhome Technologies CO.LTD

⁰