Single image super-resolution via blind blurring estimation and anchored space mapping

Xiaole Zhao; Yadong Wu; Jinsha Tian; Hongying Zhang

doi:10.1007/s41095-016-0043-7

Computational Visual Media 2016, 2(1): 71-85 https://doi.org/10.1007/s41095-016-0043-7

Research Article |

Open Access | Issue | Published: 12 March 2016

Single image super-resolution via blind blurring estimation and anchored space mapping

Show Author's Information Hide Author's Information Xiaole Zhao^¹(

), Yadong Wu^¹, Jinsha Tian^¹, Hongying Zhang^²

1 School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, China.

2 School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China.

Keywords:

super-resolution (SR), dictionary learning, blurring kernel estimation (BKE), anchored space mapping (ASM), average gradient amplitude

Cite this article:

Zhao X, Wu Y, Tian J, et al. Single image super-resolution via blind blurring estimation and anchored space mapping. Computational Visual Media, 2016, 2(1): 71-85. https://doi.org/10.1007/s41095-016-0043-7

Download citation

EndNote(RIS)

BibTeX

482

Views

Downloads

Citations

Crossref

N/A

WoS

Scopus

CSCD

Abstract Full text About this article

Abstract

It has been widely acknowledged that learning-based super-resolution (SR) methods are effective to recover a high resolution (HR) image from a single low resolution (LR) input image. However, there exist two main challenges in learning-based SR methods currently: the quality of training samples and the demand for computation. We proposed a novel framework for single image SR tasks aiming at these issues, which consists of blind blurring kernel estimation (BKE) and SR recovery with anchored space mapping (ASM). BKE is realized via minimizing the cross-scale dissimilarity of the image iteratively, and SR recovery with ASM is performed based on iterative least square dictionary learning algorithm (ILS-DLA). BKE is capable of improving the compatibility of training samples and testing samples effectively and ASM can reduce consumed time during SR recovery radically. Moreover, a selective patch processing (SPP) strategy measured by average gradient amplitude $|$ grad $|$ of a patch is adopted to accelerate the BKE process. The experimental results show that our method outruns several typical blind and non-blind algorithms on equal conditions.

Full text

Abstract

Full text

Outline

About this article

Single image super-resolution via blind blurring estimation and anchored space mapping

Show Author's information Hide Author's Information Xiaole Zhao^¹(

), Yadong Wu^¹, Jinsha Tian^¹, Hongying Zhang^²

1 School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, China.

2 School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China.

Abstract

Keywords: super-resolution (SR), dictionary learning, blurring kernel estimation (BKE), anchored space mapping (ASM), average gradient amplitude

References(34)

[1]

Freedman, G.; Fattal, R. Image and video upscaling from local self-examples. ACM Transactions on Graphics Vol. 30, No. 2, Article No. 12, 2011.

DOI Google Scholar

[2]

Babacan, S. D.; Molina, R.; Katsaggelos, A. K. Parameter estimation in TV image restoration using variational distribution approximation. IEEE Transactions on Image Processing Vol. 17, No. 3, 326-339, 2008.

DOI Google Scholar

[3]

Babacan, S. D.; Molina, R.; Katsaggelos, A. K. Total variation super resolution using a variational approach. In: Proceedings of the 15th IEEE International Conference on Image Processing, 641-644, 2008.

DOI

[4]

Babacan, S. D.; Molina, R.; Katsaggelos, A. K. Variational Bayesian super resolution. IEEE Transactions on Image Processing Vol. 20, No. 4, 984-999, 2011.

DOI Google Scholar

[5]

Sun, J.; Xu, Z.; Shum, H.-Y. Image super-resolution using gradient profile prior. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, 1-8, 2008.

[6]

Freeman, W. T.; Jones, T. R.; Pasztor, E. C. Example-based super-resolution. IEEE Computer Graphics and Applications Vol. 22, No. 2, 56-65, 2002.

DOI Google Scholar

[7]

Sun, J.; Zheng, N.-N.; Tao, H.; Shum, H.-Y. Image hallucination with primal sketch priors. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 729-736, 2003.

[8]

Chang, H.; Yeung, D. Y.; Xiong, Y. Super-resolution through neighbor embedding. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 275-282, 2004.

[9]

Roweis, S. T.; Saul, L. K. Nonlinear dimensionality reduction by locally linear embedding. Science Vol. 290, No. 5, 2323-2326, 2000.

DOI Google Scholar

[10]

Bevilacqua, M.; Roumy, A.; Guillemot, C.; Morel, M.-L. A. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the 23rd British Machine Vision Conference, 135.1-135.10, 2012.

DOI

[11]

Yang, J.; Wright, J.; Huang, T.; Ma, Y. Image super-resolution as sparse representation of raw image patches. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2008.

[12]

Glasner, D.; Bagon, S.; Irani, M. Super-resolution from a single image. In: Proceedings of IEEE 12th International Conference on Computer Vision, 349-356, 2009.

DOI

[13]

Yang, J.; Wang, Z.; Lin, Z.; Cohen, S.; Huang, T. Coupled dictionary training for image super-resolution. IEEE Transactions on Image Processing Vol. 21, No. 8, 3467-3478, 2012.

DOI Google Scholar

[14]

Yang, J.; Wright, J.; Huang, T.; Ma, Y. Image super-resolution via sparse representation. IEEE Transactions on Image Processing Vol. 19, No. 11, 2861-2873, 2010.

DOI Google Scholar

[15]

He, L.; Qi, H.; Zaretzki, R. Beta process joint dictionary learning for coupled feature spaces with application to single image super-resolution. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 345-352, 2013.

DOI

[16]

Zhao, X.; Wu, Y.; Tian, J.; Zhang, H. Single image super-resolution via blind blurring estimation and dictionary learning. In: Communications in Computer and Information Science, Vol. 546. Zha, H.; Chen, X.; Wang, L.; Miao, Q. Eds. Springer Berlin Heidelberg, 22-33, 2015.

DOI

[17]

Timofte, R.; De, V.; Van Gool, L. Anchored neighborhood regression for fast example-based super-resolution. In: Proceedings of IEEE International Conference on Computer Vision, 1920-1927, 2013.

DOI

[18]

Zontak, M.; Irani, M. Internal statistics of a single natural image. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 977-984, 2011.

DOI

[19]

Yang, C.-Y.; Huang, J.-B.; Yang, M.-H. Exploiting self-similarities for single frame super-resolution. In: Lecture Notes in Computer Science, Vol. 6594. Kimmel, R.; Klette, R.; Sugimoto, A. Eds. Springer Berlin Heidelberg, 497-510, 2010.

[20]

Zoran, D.; Weiss, Y. From learning models of natural image patches to whole image restoration. In: Proceedings of IEEE International Conference on Computer Vision, 479-486, 2011.

DOI

[21]

Hu, J.; Luo, Y. Single-image superresolution based on local regression and nonlocal self-similarity. Journal of Electronic Imaging Vol. 23, No. 3, 033014, 2014.

DOI Google Scholar

[22]

Zhang, Y.; Liu, J.; Yang, S.; Guo, Z. Joint image denoising using self-similarity based low-rank approximations. In: Proceedings of Visual Communications and Image Processing, 1-6, 2013.

DOI

[23]

Michaeli, T.; Irani, M. Blind deblurring using internal patch recurrence. In: Lecture Notes in Computer Science, Vol. 8691. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer International Publishing, 783-798, 2014.

[24]

Guillemot, C.; Le Meur, O. Image inpainting: Overview and recent advances. IEEE Signal Processing Magazine Vol. 31, No. 1, 127-144, 2014.

DOI Google Scholar

[25]

Michaeli, T.; Irani, M. Nonparametric blind super-resolution. In: Proceedings of IEEE International Conference on Computer Vision, 945-952, 2013.

DOI

[26]

Engan, K.; Skretting, K.; Husøy, J. H. Family of iterative LS-based dictionary learning algorithms, ILS-DLA, for sparse signal representation. Digital Signal Processing Vol. 17, No. 1, 32-49, 2007.

DOI Google Scholar

[27]

Timofte, R.; De Smet, V.; Van Gool, L. A+: Adjusted anchored neighborhood regression for fast super-resolution. In: Lecture Notes in Computer Science, Vol. 9006. Cremers, D.; Reid, I.; Saito, H.; Yang, M.-H. Eds. Springer International Publishing, 111-126, 2014.

[28]

Bevilacqua, M.; Roumy, A.; Guillemot, C.; Morel, M.-L. A. Super-resolution using neighbor embedding of back-projection residuals. In: Proceedings of the 18th International Conference on Digital Signal Processing, 1-8, 2013.

DOI

[29]

Irani, M.; Peleg, S. Motion analysis for image enhancement: Resolution, occlusion, and transparency. Journal of Visual Communication and Image Representation Vol. 4, No. 4, 324-335, 1993.

DOI Google Scholar

[30]

Irani, M.; Peleg, S. Improving resolution by image registration. CVGIP: Graphical Models and Image Processing Vol. 53, No. 3, 231-239, 1991.

DOI Google Scholar

[31]

Dong, C.; Chen, C. L.; He, K.; Tang, X. Learning a deep convolutional network for image super-resolution. In: Lecture Notes in Computer Science, Vol. 8692. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer International Publishing, 184-199, 2014.

[32]

Zeyde, R.; Elad, M.; Protter, M. On single image scale-up using sparse-representations. In: Lecture Notes in Computer Science, Vol. 6920. Boissonnat, J.-D.; Chenin, P.; Cohen, A. et al. Eds. Springer Berlin Heidelberg, 711-730, 2010.

[33]

Dai, D.; Timofte, R.; Van Gool, L. Jointly optimized regressors for image super-resolution. Computer Graphics Forum Vol. 34, No. 2, 95-104, 2015.

DOI Google Scholar

[34]

Shao, W.-Z.; Elad, M. Simple, accurate, and robust nonparametric blind super-resolution. In: Lecture Notes in Computer Science, Vol. 9219. Zhang, Y.-J. Ed. Springer International Publishing, 333-348, 2015.

DOI

About this article

Publication history

Acknowledgements

Rights and permissions

Publication history

Revised: 20 November 2015

Accepted: 02 February 2016

Published: 12 March 2016

Issue date: March 2016

Copyright

Acknowledgements

We would like to thank the authors of Ref. [34], Mr. Michael Elad and Mr. Wen-Ze Shao, for their kind help in running their blind SR method [34], which thus enables an effective comparison with their method. This work is partially supported by National Natural Science Foundation of China (Grant No. 61303127), Western Light Talent Culture Project of Chinese Academy of Sciences (Grant No. 13ZS0106), Project of Science and Technology Department of Sichuan Province (Grant Nos. 2014SZ0223 and 2015GZ0212), Key Program of Education Department of Sichuan Province (Grant Nos. 11ZA130 and 13ZA0169), and the innovation funds of Southwest University of Science and Technology (Grant No. 15ycx053).

Rights and permissions

This article is published with open access at Springerlink.com

The articles published in this journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Other papers from this open access journal are available free of charge from http://www.springer.com/journal/41095. To submit a manuscript, please go to https://www.editorialmanager.com/cvmj.