Blind Deconvolution for Noisy and Blurry Images Using Low Rank Prior
SUN Shijie①②③④ ZHAO Huaici①③④ LI Bo①②③④⑤ HAO Mingguo①③④ LÜ Jinfeng①②③④
①(Optical-Electronics Information Technology Department, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China) ②(University of Chinese Academy of Sciences, Beijing 100049, China) ③(Key Laboratory of Opto-Electronics Information Processing, Chinese Academy of Sciences, Shenyang 110016, China) ④(Key Laboratory of Image Understanding and Computer Vision, Shenyang 110016, China) ⑤(College of Information, Shenyang Institute of Engineering, Shenyang 110136, China)
The purpose of single image blind deconvolution is to estimate the unknown blur kernel from a single observed blurred image and recover the original sharp image. Such a task is severely ill-posed and even more challenging especially in the condition that the noise in the input image can not be negligible. In this paper, the main problem this study focuses on is how to effectively apply low rank prior to blind deconvolution. A single noisy and blurry image blind deconvolution algorithm is proposed, using alternating Maximum A Posteriori (MAP) estimation combined with low rank prior. First, when estimating the intermediate latent image, low rank prior is used as the constraint that is used for noise suppression of the restored image. Then the denoised intermediate latent image in turn leads to higher quality blur kernel estimation. These two operations are iterated in this manner to arrive at reliable blur kernel estimation. Finally, the non-blind deconvolution method is chosen to be used with sparse prior knowledge to achieve the final latent image restoration. Extensive experiments manifest the superiority of the proposed method over state-of-the-art techniques, both qualitatively and quantitatively.
LEVIN A, WEISS Y, DURAND F, et al. Efficient marginal likelihood optimization in blind deconvolution[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2011: 2657-2664. doi: 10.1109/CVPR. 2011.5995308.
[2]
KRISHNAN D, TAY T, and FERGUS R. Blind deconvolution using a normalized sparsity measure[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2011: 233-240. doi: 10.1109/CVPR. 2011.5995308.
[3]
SUN L, Cho S, Wang J, et al. Edge-based blur kernel estimation using patch priors[C]. IEEE Conference on Computational Photography, Cambridge, MA, USA, 2013: 1-8, 19-21. doi: 10.1109/ICCPhot.2013.6528301.
[4]
LAI W S, DING J J, LIN Y Y, et al. Blur kernel estimation using normalized color-line priors[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015: 64-72. doi: 10.1109/CVPR.2015.7298601.
[5]
REN W, CAO X, PAN J, et al. Image deblurring via enhanced low-rank prior[J]. IEEE Transactions on Image Processing, 2016, 25(7): 3426-3437. doi: 10.1109/TIP.2016. 2571062.
[6]
CHO S and LEE S. Fast motion deblurring[J]. ACM Transactions on Graphics, 2009, 28(5): 89-97. doi: 10.1145/ 1618452.1618491.
[7]
XU L and JIA J Y. Two-phase kernel estimation for robust motion deblurring[C]. European Conference on Computer Vision, Crete, Greece, 2010: 157-170. doi: 10.1007/978-3-642- 15549-9_12.
[8]
PAN J, LIU R, SU Z, et al. Kernel estimation from salient structure for robust motion deblurring[J]. Signal Processing: Image Commmunication, 2013, 28(9): 1156-1170. doi: 10. 1016/j.image.2013.05.001.
[9]
PAN J, HU Z, SU Z, et al. L0-regularized intensity and gradient prior for text images deblurring and beyond[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(2): 342-355. doi: 10.1109/TPAMI.2016. 2551244.
[10]
PAN J, SUN D, PFISTER H, et al. Blind image deblurring using dark channel prior[C]. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016: 1628-1636. doi: 10.1109/CVPR.2016.180.
[11]
MAI L and LIU F. Kernel fusion for better image deblurring[C]. IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 2015: 371-380. doi: 10.1109/CVPR.2015.7298634.
[12]
YAN R M and SHAO L. Blind image blur estimation via deep learning[J]. IEEE Transactions on Image Processing, 2016, 25(4): 1910-1921. doi: 10.1109/TIP.2016.2535273.
[13]
TAI Y and LIN S. Motion-aware noise filtering for deblurring of noisy and blurry images[C]. IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, USA, 2012: 17-24. doi: 10.1109/CVPR.2012.6247653.
[14]
ZHONG L, CHO S, METAXAS D, et al. Handling noise in single image deblurring using directional filters[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, Oregon, USA, 2013: 612-619. doi: 10.1109/CVPR. 2013.85.
[15]
WHYTE O, SIVIC J, ZISSERMAN A, et al. Non-uniform deblurring for shaken images[C]. IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010: 491-498. doi: 10.1109/CVPR.2010.5540175.
[16]
GU S, ZHANG L, ZUO W, et al. Weighted nuclear norm minimization with application to image denoising[C]. IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014: 2862-2869. doi: 10.1109/CVPR. 2014.366.
[17]
DONG W S, SHI G M, and LI X. Nonlocal image restoration with bilateral variance estimation: A low-rank approach[J]. IEEE Transactions on Image Processing, 2013, 22(2): 700-711. doi: 10.1109/TIP.2012.2221729.
[18]
CAI J F, CAND?S E J, and SHEN Z. A singular value thresholding algorithm for matrix completion[J]. SIAM Journal on Optimization, 2008, 20(4): 1956-1982. doi: 10. 1137/080738970.
[19]
NOCEDAL J and WRIGHT S. Numerical Optimization[M]. NY, USA, Springer-Verlag New York, Inc., 2006: 497-506. doi: 10.1007/978-0-387-40065-5.
[20]
LEVIN A, WEISS Y, DURAND F, et al. Understanding and evaluating blind deconvolution algorithms[C]. IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, FL, USA, 2009: 1964-1971. doi: 10.1109/ CVPR.2009.5206815.
[21]
WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. doi: 10.1109/TIP.2003.819861.
[22]
XU L, ZHENG S, and JIA J Y. Unnatural L0 sparse representation for natural image deblurring[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, Oregon, USA, 2013: 1107-1114. doi: 10.1109/ CVPR.2013.147.
