Single image super-resolution via blind blurring estimation and anchored space mapping

It has been widely acknowledged that learning-based super-resolution (SR) methods are effective to recover a high resolution (HR) image from a single low resolution (LR) input image. However, there exist two main challenges in learning-based SR methods currently: the quality of training samples and the demand for computation. We proposed a novel framework for single image SR tasks aiming at these issues, which consists of blind blurring kernel estimation (BKE) and SR recovery with anchored space mapping (ASM). BKE is realized via minimizing the cross-scale dissimilarity of the image iteratively, and SR recovery with ASM is performed based on iterative least square dictionary learning algorithm (ILS-DLA). BKE is capable of improving the compatibility of training samples and testing samples effectively and ASM can reduce consumed time during SR recovery radically. Moreover, a selective patch processing (SPP) strategy measured by average gradient amplitude |grad| of a patch is adopted to accelerate the BKE process. The experimental results show that our method outruns several typical blind and non-blind algorithms on equal conditions.

[1]  Chao Yang,et al.  Development of a Scalable Solver for the Earth's Core Convection , 2009, HPCA.

[2]  Michal Irani,et al.  Nonparametric Blind Super-resolution , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Aline Roumy,et al.  Super-resolution using neighbor embedding of back-projection residuals , 2013, 2013 18th International Conference on Digital Signal Processing (DSP).

[4]  Michal Irani,et al.  Super-resolution from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  William T. Freeman,et al.  Example-Based Super-Resolution , 2002, IEEE Computer Graphics and Applications.

[6]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[7]  Jing Hu,et al.  Single-image superresolution based on local regression and nonlocal self-similarity , 2014, J. Electronic Imaging.

[8]  Jiaying Liu,et al.  Joint image denoising using self-similarity based low-rank approximations , 2013, 2013 Visual Communications and Image Processing (VCIP).

[9]  Michal Irani,et al.  Internal statistics of a single natural image , 2011, CVPR 2011.

[10]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

[11]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[12]  Michal Irani,et al.  Improving resolution by image registration , 1991, CVGIP Graph. Model. Image Process..

[13]  Yadong Wu,et al.  Single image super-resolution via blind blurring estimation and dictionary learning , 2015, Neurocomputing.

[14]  Luc Van Gool,et al.  A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution , 2014, ACCV.

[15]  Russell Zaretzki,et al.  Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[17]  Michael Elad,et al.  Simple, Accurate, and Robust Nonparametric Blind Super-Resolution , 2015, ICIG.

[18]  Raanan Fattal,et al.  Image and video upscaling from local self-examples , 2011, TOGS.

[19]  Luc Van Gool,et al.  Jointly Optimized Regressors for Image Super‐resolution , 2015, Comput. Graph. Forum.

[20]  Aggelos K. Katsaggelos,et al.  Total variation super resolution using a variational approach , 2008, 2008 15th IEEE International Conference on Image Processing.

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

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

[23]  Christine Guillemot,et al.  Image Inpainting : Overview and Recent Advances , 2014, IEEE Signal Processing Magazine.

[24]  Kjersti Engan,et al.  Family of iterative LS-based dictionary learning algorithms, ILS-DLA, for sparse signal representation , 2007, Digit. Signal Process..

[25]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[26]  Aggelos K. Katsaggelos,et al.  Parameter Estimation in TV Image Restoration Using Variational Distribution Approximation , 2008, IEEE Transactions on Image Processing.

[27]  Thomas S. Huang,et al.  Image super-resolution as sparse representation of raw image patches , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Hong Chang,et al.  Super-resolution through neighbor embedding , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[29]  Nanning Zheng,et al.  Image hallucination with primal sketch priors , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[30]  Chih-Yuan Yang,et al.  Exploiting Self-similarities for Single Frame Super-Resolution , 2010, ACCV.

[31]  Thomas S. Huang,et al.  Coupled Dictionary Training for Image Super-Resolution , 2012, IEEE Transactions on Image Processing.

[32]  Aggelos K. Katsaggelos,et al.  Variational Bayesian Super Resolution , 2011, IEEE Transactions on Image Processing.

[33]  Luc Van Gool,et al.  Anchored Neighborhood Regression for Fast Example-Based Super-Resolution , 2013, 2013 IEEE International Conference on Computer Vision.

[34]  Aline Roumy,et al.  Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding , 2012, BMVC.