AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (4 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Image Blind Deblurring Using an Adaptive Patch Prior

Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
Show Author Information

Abstract

Image blind deblurring uses an estimated blur kernel to obtain an optimal restored original image with sharp features from a degraded image with blur and noise artifacts. This method, however, functions on the premise that the kernel is estimated accurately. In this work, we propose an adaptive patch prior for improving the accuracy of kernel estimation. Our proposed prior is based on local patch statistics and can rebuild low-level features, such as edges, corners, and junctions, to guide edge and texture sharpening for blur estimation. Our prior is a nonparametric model, and its adaptive computation relies on internal patch information. Moreover, heuristic filters and external image knowledge are not used in our prior. Our method for the reconstruction of salient step edges in a blurry patch can reduce noise and over-sharpening artifacts. Experiments on two popular datasets and natural images demonstrate that the kernel estimation performance of our method is superior to that of other state-of-the-art methods.

Keywords

blind deblurringadaptive patch priorkernel estimationlow-level featuresinternal patch information

References

[1]
Fergus R., Singh B., Hertzmann A., Roweis S. T., and Freeman W. T., Removing camera shake from a single photograph, ACM Transactions on Graphics, vol. 25, no. 3, pp. 787-794, 2006.
Crossref Google Scholar
[2]
Shan Q., Jia J., and Agarwala A., High-quality motion deblurring from a single image, ACM Transactions on Graphics, vol. 27, no. 3, pp. 15-19, 2008.
Crossref Google Scholar
[3]
Levin A., Weiss Y., Durand F., and Freeman W. T., High-quality motion deblurring from a single image, IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 12, pp. 2354-2367, 2011.
Crossref Google Scholar
[4]
Levin A., Weiss Y., Durand F., and Freeman W. T., Efficient marginal likelihood optimization in blind deconvolution, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011, pp. 2657-2664.
Crossref
[5]
Krishnan D., Tay T., and Fergus R., Blind deconvolution using a normalized sparsity measure, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011, pp. 233-240.
Crossref
[6]
Pan J. and Su Z., Fast ℓ0-regularized kernel estimation for robust motion deblurring, IEEE Signal Processing Letters, vol. 20, no. 9, pp. 841-844, 2013.
Crossref Google Scholar
[7]
Perrone D. and Favaro P., Total variation blind deconvolution: The devil is in the details, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 2909-2916.
Crossref
[8]
Bronstein M. M., Bronstein A. M., Zibulevsky M., and Zeevi Y. Y., Blind deconvolution of images using optimal sparse representations, IEEE Trans. Image Processing, vol. 14, no. 6, pp. 726-736, 2005.
Crossref Google Scholar
[9]
Zhang H., Yang J., and Zhang Y., Sparse representation based blind image deblurring, in Proc. IEEE Conf. Multimedia and Expo, Barcelona, Spain, 2011, pp. 1-6.
[10]
Yu J., Chang Z., Xiao C., and Sun W., Blind image deblurring based on sparse representation and structural self-similarity, in Proc. IEEE Conf. Acoustics, Speech and Signal Processing, New Orleans, LA, USA, 2017, pp. 1328-1332.
Crossref
[11]
Joshi N., Szeliski R., and Kriegman D. J., PSF estimation using sharp edge prediction, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, AK, USA, 2008, pp. 1-8.
Crossref
[12]
Cho S. and Lee S., Fast motion deblurring, ACM Transactions on Graphics, vol. 28, no. 5, pp. 89-97, 2009.
Crossref Google Scholar
[13]
Xu L. and Jia J., Two-phase kernel estimation for robust motion deblurring, in Proc. European Conf. Computer Vision, 2010, pp. 157-170.
Crossref
[14]
Cho T. S., Paris S., Horn B. K., and Freeman W. T., Blur kernel estimation using the radon transform, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011, pp. 241-248.
Crossref
[15]
Zhou Y. and Komodakis N., A MAP-estimation framework for blind deblurring using high-level edge priors, in Proc. European Conf. Computer Vision, Cham, Switzerland, 2014, pp. 142-157.
Crossref
[16]
Sun L., Cho S., and Wang J., Edge-based blur kernel estimation using patch priors, in Proc. IEEE Conf. Computational Photography, Cambridge, MA, USA, 2013, pp. 1-8.
[17]
Michaeli T. and Irani M., Blind deblurring using internal patch recurrence, in Proc. European Conf. Computer Vision, Cham, Switzerland, 2014, pp. 783-798.
Crossref
[18]
Lai W. S., Ding J. J., Lin Y. Y., and Chuang Y. Y., Blur kernel estimation using normalized color-line prior, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Boston, MA, USA, 2015, pp. 64-72.
[19]
Ren W., Cao X., Pan J., Guo X., Zuo W., and Yang M., Image deblurring via enhanced low-rank prior, IEEE Trans. Image Processing, vol. 25, no. 7, pp. 3426-3437, 2016.
Crossref Google Scholar
[20]
Hacohen Y., Shechtman E., and Lischinski D., Deblurring by example using dense correspondence, in Proc. IEEE Conf. Computer Vision, Sydney, Australia, 2013, pp. 2384-2391.
Crossref
[21]
Kenig T., Kam Z., and Feuer A., Blind image deconvolution using machine learning for three-dimensional microscopy, IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 12, pp. 2191-2204, 2010.
Crossref Google Scholar
[22]
Pan J., Sun D., Pfister H., and Yang M. H., Blind image deblurring using dark channel prior, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 1628-1636.
Crossref
[23]
Yan Y., Ren W., Guo Y., Wang R., and Cao X., Image deblurring via extreme channels prior, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 6978-6986.
Crossref
[24]
Ren W., Pan J., Cao X., and Yang M., Video deblurring via semantic segmentation and pixel-wise non-linear kernel, in Proc. IEEE Conf. Computer Vision, Venice, Italy, 2017, pp. 1086-1094.
Crossref
[25]
Perrone D. and Favaro P., A logarithmic image prior for blind deconvolution, International Journal of Computer Vision, vol. 117, no. 2, pp. 159-172, 2016.
Crossref Google Scholar
[26]
Szeliski R., Computer Vision: Algorithms and Applications. Springer Science+Business Media, 2010.
[27]
Liu J., Li W., and Tian Y., Automatic thresholding of gray-level pictures using two-dimension Otsu method, in Proc. IEEE Conf. Circuits and Systems, Shenzhen, China, 1991, pp. 325-327.
[28]
Zontak M. and Irani M., Internal statistics of a single natural image, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Colorado Springs, CO, USA, 2011, pp. 977-984.
Crossref
[29]
Joshi N., Zitnick C. L., Szeliski R., and Kriegman D. J., Image deblurring and denoising using color priors, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Miami, FL, USA, 2009, pp. 1550-1557.
Crossref
[30]
Zoran D. and Weiss Y., From learning models of natural image patches to whole image restoration, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Barcelona, Spain, 2011, pp. 479-486.
Crossref
Tsinghua Science and Technology
Volume 24 Issue 2,
April 2019
Pages 238-248
DOI: 10.26599/TST.2018.9010123
Cite this article:
Guo Y, Ma H. Image Blind Deblurring Using an Adaptive Patch Prior. Tsinghua Science and Technology, 2019, 24(2): 238-248. https://doi.org/10.26599/TST.2018.9010123

801

Views

30

Downloads

9

Crossref

N/A

Web of Science

10

Scopus

0

CSCD

Altmetrics
Received: 05 June 2018
Revised: 04 September 2018
Accepted: 07 September 2018
Published: 31 December 2018
© The author(s) 2019
Return