A Clearer Picture of Total Variation Blind Deconvolution

Blind deconvolution is the problem of recovering a sharp image and a blur kernel from a noisy blurry image. Recently, there has been a significant effort on understanding the basic mechanisms to solve blind deconvolution. While this effort resulted in the deployment of effective algorithms, the theoretical findings generated contrasting views on why these approaches worked. On the one hand, one could observe experimentally that alternating energy minimization algorithms converge to the desired solution. On the other hand, it has been shown that such alternating minimization algorithms should fail to converge and one should instead use a so-called Variational Bayes approach. To clarify this conundrum, recent work showed that a good image and blur prior is instead what makes a blind deconvolution algorithm work. Unfortunately, this analysis did not apply to algorithms based on total variation regularization. In this manuscript, we provide both analysis and experiments to get a clearer picture of blind deconvolution. Our analysis reveals the very reason why an algorithm based on total variation works. We also introduce an implementation of this algorithm and show that, in spite of its extreme simplicity, it is very robust and achieves a performance comparable to the top performing algorithms.

[1]  Subhasis Chaudhuri,et al.  Joint MAP estimation for blind deconvolution: when does it work? , 2012, ICVGIP '12.

[2]  Daniel Cremers,et al.  An approach to vectorial total variation based on geometric measure theory , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Seungyong Lee,et al.  Fast motion deblurring , 2009, ACM Trans. Graph..

[4]  P. Davies,et al.  Local Extremes, Runs, Strings and Multiresolution , 2001 .

[5]  Li Xu,et al.  Unnatural L0 Sparse Representation for Natural Image Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[7]  Aggelos K. Katsaggelos,et al.  Bayesian Blind Deconvolution with General Sparse Image Priors , 2012, ECCV.

[8]  Jiaya Jia,et al.  High-quality motion deblurring from a single image , 2008, ACM Trans. Graph..

[9]  Sylvain Paris,et al.  Handling Noise in Single Image Deblurring Using Directional Filters , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Frédo Durand,et al.  Understanding and evaluating blind deconvolution algorithms , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Takahiro Saito,et al.  Three kinds of color total-variation semi-norms and its application to color-image denoising , 2011, 2011 18th IEEE International Conference on Image Processing.

[12]  David Mumford,et al.  Statistics of natural images and models , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[13]  Haichao Zhang,et al.  Analysis of Bayesian Blind Deconvolution , 2013, EMMCVPR.

[14]  Mostafa Kaveh,et al.  Anisotropic blind image restoration , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[15]  Michal Irani,et al.  Blind Deblurring Using Internal Patch Recurrence , 2014, ECCV.

[16]  Tony F. Chan,et al.  Total variation blind deconvolution , 1998, IEEE Trans. Image Process..

[17]  Bernhard Schölkopf,et al.  Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database , 2012, ECCV.

[18]  Daniele Perrone,et al.  Total Variation Blind Deconvolution: The Devil Is in the Details , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Subhasis Chaudhuri,et al.  Blind Image Deconvolution , 2014, Springer International Publishing.

[20]  Ligang Liu,et al.  A Local/Global Approach to Mesh Parameterization , 2008, Comput. Graph. Forum.

[21]  Andrew Zisserman,et al.  Deblurring shaken and partially saturated images , 2011, ICCV Workshops.

[22]  David J. C. MacKay,et al.  Ensemble Learning for Blind Image Separation and Deconvolution , 2000 .

[23]  Rob Fergus,et al.  Blind deconvolution using a normalized sparsity measure , 2011, CVPR 2011.

[24]  Li Xu,et al.  Two-Phase Kernel Estimation for Robust Motion Deblurring , 2010, ECCV.

[25]  T. Chan,et al.  Convergence of the alternating minimization algorithm for blind deconvolution , 2000 .

[26]  Yair Weiss,et al.  From learning models of natural image patches to whole image restoration , 2011, 2011 International Conference on Computer Vision.

[27]  Frédo Durand,et al.  Understanding Blind Deconvolution Algorithms , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  T. Chan,et al.  Edge-preserving and scale-dependent properties of total variation regularization , 2003 .

[29]  Raanan Fattal,et al.  Blur-Kernel Estimation from Spectral Irregularities , 2012, ECCV.

[30]  Sunghyun Cho,et al.  Edge-based blur kernel estimation using patch priors , 2013, IEEE International Conference on Computational Photography (ICCP).

[31]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[32]  Daniele Perrone,et al.  Blind Deconvolution via Lower-Bounded Logarithmic Image Priors , 2015, EMMCVPR.

[33]  Frédo Durand,et al.  Efficient marginal likelihood optimization in blind deconvolution , 2011, CVPR 2011.

[34]  Lin He,et al.  Blind deconvolution using TV regularization and Bregman iteration , 2005, Int. J. Imaging Syst. Technol..

[35]  Sundaresh Ram,et al.  Removing Camera Shake from a Single Photograph , 2009 .

[36]  Mostafa Kaveh,et al.  A regularization approach to joint blur identification and image restoration , 1996, IEEE Trans. Image Process..

[37]  Shiqiang Yang,et al.  Multi-scale blind motion deblurring using local minimum , 2009 .

[38]  Frédo Durand,et al.  Image and depth from a conventional camera with a coded aperture , 2007, ACM Trans. Graph..

[39]  Laurent Condat,et al.  A Direct Algorithm for 1-D Total Variation Denoising , 2013, IEEE Signal Processing Letters.

[40]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[41]  Tony F. Chan,et al.  Color TV: total variation methods for restoration of vector-valued images , 1998, IEEE Trans. Image Process..