Fast ℓ0-Regularized Kernel Estimation for Robust Motion Deblurring

被引：55

作者：

机构：

[1] School of Mathematical Sciences, Dalian University of Technology

来源：

| 1600年 / Institute of Electrical and Electronics Engineers Inc., United States卷 / 20期

关键词：

ℓ[!sup]0[!/sup]-regularized method; blind image deblurring; image restoration; kernel estimation;

D O I：

10.1109/LSP.2013.2261986

中图分类号：

学科分类号：

摘要：

Blind image deblurring is a challenging problem in computer vision and image processing. In this paper, we propose a new ℓ0-regularized approach to estimate a blur kernel from a single blurred image by regularizing the sparsity property of natural images. Furthermore, by introducing an adaptive structure map in the deblurring process, our method is able to restore useful salient edges for kernel estimation. Finally, we propose an efficient algorithm which can solve the proposed model efficiently. Extensive experiments compared with state-of-the-art blind deblurring methods demonstrate the effectiveness of the proposed method. © 1994-2012 IEEE.

引用

页码：841 / 844

页数：3

共 19 条

[1]

Fergus R., Singh B., Hertzmann A., Roweis S.T., Freeman W.T., Removing camera shake from a single photograph, ACM Transactions on Graphics, 25, 3, pp. 787-794, (2006)

[2]

Shan Q., Jia J., Agarwala A., High-quality motion deblurring from a single image, ACM Trans. Graph., 27, 3, (2008)

[3]

Cho S., Lee S., Fastmotion deblurring, ACM Trans. Graph., 28, 5, (2009)

[4]

Krishnan D., Tay T., Fergus R., Blind deconvolution using a normalized sparsity measure, Proc. IEEE Conf. Comput. Vision and Pattern Recognit.0, pp. 2657-2664, (2011)

[5]

Xu L., Jia J., Two-hase kernel estimation for robust motion deblurring, Proc. Eur. Conf. Comput. Vision, pp. 157-170, (2010)

[6]

Levin A., Weiss Y., Durand F., Freeman W.T., Understanding and evaluating blind deconvolution algorithms, Proc. IEEE Conf. Comput. Vision and Pattern Recognit., pp. 1964-1971, (2009)

[7]

Hu Z., Yang M.-H., Good regions to deblur, Proc. Eur. Conf. Comput. Vision, pp. 59-72, (2012)

[8]

Tai Y.-W., Lin S., Motion-aware noise filtering for deblurring of noisy and blurry images, Proc. IEEE Conf. Comput. Vision and Pattern Recognit., pp. 17-24, (2012)

[9]

Levin A., Weiss Y., Durand F., Freeman W.T., Efficient marginal likelihood optimization in blind deconvolution, Proc. IEEE Conf. Comput. Vision and Pattern Recognit., pp. 2657-2664, (2011)

[10]

Chan T.F., Wong C.-K., Total variation blind deconvolution, IEEE Transactions on Image Processing, 7, 3, pp. 370-375, (1998)

← 1 2 →