Abstract
This paper proposes a patch-based deblurring method to leverage the unregistered sharp example image which shares global or local contents with the blurred image in a variant view. Firstly, we propose a coarse-to-fine scheme to achieve the accurate image patches matching and solve the mismatch problem caused by the blur ambiguity. Secondly, we use sharp image patches to form a patch prior which outperforms the generic prior in kernel estimation as it retain more image details which are usually filtered out using generic priors. The proposed method using unregistered sharp example image make it more practical to find examples from variant ways, e.g. the Internet, the succession capturing using hand-held camera, and multi-frame in videos. Experiments on real-world images show the patch prior can achieve more accurate and robust kernel estimation and outperforms state-of-the-art methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR, pp. 1964–1971 (2009)
Xu, L., Jia, J.: Two-phase kernel estimation for robust motion deblurring. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 157–170. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15549-9_12
Michaeli, T., Irani, M.: Blind deblurring using internal patch recurrence. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 783–798. Springer, Cham (2014). doi:10.1007/978-3-319-10578-9_51
Pan, J., Hu, Z., Su, Z., Yang, M.H.: L0-regularized intensity and gradient prior for deblurring text images and beyond. IEEE TPAMI 99, 1–14 (2016)
Gong, D., Tan, M., Zhang, Y., van den Hengel, A., Shi, Q.: Blind image deconvolution by automatic gradient activation. In: CVPR, pp. 1827–1836 (2016)
Gong, D., Yang, J., Liu, L., Zhang, Y., Reid, I., Shen, C., Hengel, A.V.D., Shi, Q.: From motion blur to motion flow: a deep learning solution for removing heterogeneous motion blur. In: CVPR (2017)
Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. In: NIPS, pp. 1033–1041 (2009)
Sun, L., Cho, S., Wang, J., Hays, J.: Good image priors for non-blind deconvolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 231–246. Springer, Cham (2014). doi:10.1007/978-3-319-10593-2_16
Hu, Z., Yuan, L., Lin, S., Yang, M.: Image deblurring using smartphone inertial sensors. In: CVPR, pp. 1855–1864 (2016)
Cho, S., Lee, S.: Fast motion deblurring. ACM Trans. Graph. 28(5), 145:1–145:8 (2009)
Zhang, H., Wipf, D.P., Zhang, Y.: Multi-image blind deblurring using a coupled adaptive sparse prior. In: CVPR, pp. 1051–1058 (2013)
Zhu, X., Šroubek, F., Milanfar, P.: Deconvolving PSFs for a better motion deblurring using multiple images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 636–647. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33715-4_46
Yuan, L., Sun, J., Quan, L., Shum, H.: Image deblurring with blurred/noisy image pairs. ACM Trans. Graph. 26(3), 1 (2007)
HaCohen, Y., Shechtman, E., Lischinski, D.: Deblurring by example using dense correspondence. In: ICCV, pp. 2384–2391 (2013)
Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration (2011)
Zhu, Y., Zhang, Y., Yuille, A.L.: Single image super-resolution using deformable patches. In: CVPR, pp. 2917–2924 (2014)
Olonetsky, I., Avidan, S.: TreeCANN - k-d tree coherence approximate nearest neighbor algorithm. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 602–615. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33765-9_43
Xu, L., Zheng, S., Jia, J.: Unnatural L0 sparse representation for natural image deblurring. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 23–28 June 2013, pp. 1107–1114 (2013)
Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: CVPR, pp. 233–240 (2011)
Hu, Z., Yang, M.-H.: Good regions to deblur. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 59–72. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33715-4_5
Hu, Z., Yang, M.-H.: Learning good regions to deblur images. Int. J. Comput. Vision 115(3), 345–362 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Chen, X., Zhu, Y., Sun, W., Zhang, Y. (2017). Example-Guided Image Prior for Blind Image Deblurring. In: Sun, Y., Lu, H., Zhang, L., Yang, J., Huang, H. (eds) Intelligence Science and Big Data Engineering. IScIDE 2017. Lecture Notes in Computer Science(), vol 10559. Springer, Cham. https://doi.org/10.1007/978-3-319-67777-4_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-67777-4_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67776-7
Online ISBN: 978-3-319-67777-4
eBook Packages: Computer ScienceComputer Science (R0)