Interleaved Regression Tree Field Cascades for Blind Image Deconvolution

Image blur from camera shake is a common cause for poor image quality in digital photography, prompting a significant recent interest in image deblurring. The vast majority of work on blind deblurring splits the problem into two subsequent steps: First, the blur process (i.e., blur kernel) is estimated, then the image is restored given the estimated kernel using a non-blind deblurring algorithm. Recent work in non-blind deblurring has shown that discriminative approaches can have clear image quality and runtime benefits over typical generative formulations. In this paper, we propose a cascade for blind deblurring that alternates between kernel estimation and discriminative deblurring using regression tree fields (RTFs). We further contribute a new dataset of realistic image blur kernels from human camera shake, which we use to train the discriminative component. Extensive qualitative and quantitative experiments show a clear gain in image quality by interleaving kernel estimation and discriminative deblurring in an iterative cascade.

[1]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Stefan Roth,et al.  Shrinkage Fields for Effective Image Restoration , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Sunghyun Cho,et al.  Good Image Priors for Non-blind Deconvolution - Generic vs. Specific , 2014, ECCV.

[4]  Dacheng Tao,et al.  Recent Progress in Image Deblurring , 2014, ArXiv.

[5]  Frédo Durand,et al.  Understanding and evaluating blind deconvolution algorithms , 2009, CVPR.

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

[7]  Stefan Roth,et al.  Bayesian deblurring with integrated noise estimation , 2011, CVPR 2011.

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

[9]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[10]  William T. Freeman,et al.  Removing camera shake from a single photograph , 2006, SIGGRAPH 2006.

[11]  Richard Szeliski,et al.  PSF estimation using sharp edge prediction , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Rob Fergus,et al.  Fast Image Deconvolution using Hyper-Laplacian Priors , 2009, NIPS.

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

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

[15]  Sebastian Nowozin,et al.  Discriminative Non-blind Deblurring , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[17]  Sunghyun Cho,et al.  Fast motion deblurring , 2009, SIGGRAPH 2009.

[18]  Bernhard Schölkopf,et al.  A Machine Learning Approach for Non-blind Image Deconvolution , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Sebastian Nowozin,et al.  Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art , 2012, ECCV.

[20]  Sebastian Nowozin,et al.  Regression Tree Fields — An efficient, non-parametric approach to image labeling problems , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[22]  S. B. Kang,et al.  Image deblurring using inertial measurement sensors , 2010, SIGGRAPH 2010.

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

[24]  Qi Gao,et al.  How Well Do Filter-Based MRFs Model Natural Images? , 2012, DAGM/OAGM Symposium.

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

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

[27]  Edward H. Adelson,et al.  Learning Gaussian Conditional Random Fields for Low-Level Vision , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[29]  Jean Ponce,et al.  Non-uniform Deblurring for Shaken Images , 2012, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

[32]  ZissermanAndrew,et al.  The Pascal Visual Object Classes Challenge , 2015 .

[33]  Karen O. Egiazarian,et al.  Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-Image Raw-Data , 2008, IEEE Transactions on Image Processing.

[34]  Bernhard Schölkopf,et al.  Fast removal of non-uniform camera shake , 2011, 2011 International Conference on Computer Vision.

[35]  Sebastian Nowozin,et al.  Cascades of Regression Tree Fields for Image Restoration , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.