Abstract
Non-uniform motion deblurring is a hard topic for image processing. Non-uniform blur is often caused by camera motion in 3D while taking photos. Existing non-uniform deblurring methods formulate the blur as a linear combination of homographic transforms of a clear image. But they are computationally expensive and require large memory because the amount of the unknown variables are large. In this paper we use patch-wise method for the deblurring process. The patch-wise method are proved to be an effective method for non-uniform motion deblurring. The key issues are the accuracy of kernel estimation and the substitution of the erroneous kernels. In this paper, we use normalized smoothing term for the blur kernel estimation because it is effective and stable. When the erroneous kernels are conformed, we use a minimization method using neighborhood information for estimating the kernels. Experiments demonstrate the validity of the proposed method.
Chapter PDF
References
Chan, T., Wong, C.: Total variation blind deconvolution. IEEE Tran. Image Processing 7(3), 370–375 (1998)
Fergus, R., Singh, B., Hertzmann, A., et al.: Removing camera shake from a single photograph. ACM Transaction on Graphics 25(3), 787–794 (2006)
Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. ACM Transaction on Graphics 27(3), 731–740 (2008)
Levin, A., Weiss, Y., Durand, E., et al.: Understanding and evaluating blind deconvolution algorithms. CVPR:1964-1971 (2009)
Hui, J., Liu, C.: Motion blur identification from image gradients. CVPR (2008)
Cho, S., Lee, S.: Fast motion deblurring. ACM Transaction on Graphics 28(5), 1450–1451 (2009)
Xu, L., Jia, J.: Two-Phase Kernel Estimation for Robust Motion Deblurring. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 157–170. Springer, Heidelberg (2010)
Hong, H., Park, K.: Single-image motion deblurring using adaptive anisotropic regularization. Optical Engineering 49(9), 097008-1–097008-13 (2010)
Xu, L., Zheng, Sh., Jia, J.: Unnatural L0 Sparse Representation for Natural Image Deblurring. CVPR (2013)
Hurley, N., Rickard, S.: Comparing measures of sparsity. IEEE Trans. Inf. Theory pp. 4723–4741 (2009)
Krishnan, D., Tay, T., Fergus, R.: Blind deconvolution using a normalized sparsity measure. In: CVPR, pp. 233–240 (2011)
Xu, L., Lu, C., Xu, Y., Jia, J.: Image Smoothing via L0 Gradient Minimization. ACM Transactions on Graphics 30(6), 1741–1752 (2011)
Osher, S., Mao, Y., Dong, B., et al.: Fast linearized bregman iteration for compressive sensing and sparse denoising. Commun. Math. Sci. 8(1), 93–111 (2010)
Levin, A., Fergus, R., Durand, F., et al.: Image and depth from a conventional camera with a coded aperture. ACM Transaction on Graphics 26(3), 701–709 (2007)
Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D 60, 259–268 (1992)
Whyte, O., Sivic, J., Zisserman, A., Ponce, J.: Non-uniform Deblurring for Shaken Images. In: CVPR (2010)
Gupta, A., Joshi, N., Lawrence Zitnick, C., Cohen, M., Curless, B.: Single Image Deblurring Using Motion Density Functions. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 171–184. Springer, Heidelberg (2010)
Harmeling, S., Hirsch, M., Schölkopf, B.: Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake. NIPS 2010
Hirsch, M., Schuler, C., Harmeling, S., Schölkopf, B.: Fast Removal of Non-uniform Camera Shake. In: ICCV (2011)
Ji, H., Wang, K.: A two-stage approach to blind spatially-varying motion deblurring. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 73–80. IEEE (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, G., Wei, B., Pan, Z., Lu, J., Diao, Z. (2015). Non-uniform Motion Deblurring Using Normalized Hyper Laplacian Prior. In: Zha, H., Chen, X., Wang, L., Miao, Q. (eds) Computer Vision. CCCV 2015. Communications in Computer and Information Science, vol 546. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48558-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-662-48558-3_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48557-6
Online ISBN: 978-3-662-48558-3
eBook Packages: Computer ScienceComputer Science (R0)