Example-based image super-resolution via blur kernel estimation and variational reconstruction

Abstract Single image super-resolution aims at generating clear high-resolution image from one low-resolution image. Due to the limited low-resolution information, it is a challenging task to restore clear, artifacts-free image, meanwhile preserving finer structures and textures. This paper proposes an effective example-based image super-resolution method while making clear image and no compromise on quality. Firstly, the image prior is imposed on the anchor neighborhood regression model to optimize mapping coefficient for interim latent image construction. In order to remove its blur, kernel estimation iteration optimization algorithm is proposed based on the salient edges which are extracted through texture-structure discriminate minimum energy function and fractional order mask enhancement. Finally, an accurate reconstruction constraint combined with a simple gradient regularization is applied to reconstruct the super-resolution image. The proposed method is able to produce clear high-frequency texture details and maintain clean edges even under large scaling factors. Experimental results show that the proposed method performs well in visual effects and similarities. Furthermore, we test our algorithm in multi-texture images for robust evaluation. It is demonstrated that our algorithm is robust under complicated textures condition.

[1]  Zhe L. Lin,et al.  Fast Image Super-Resolution Based on In-Place Example Regression , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Francisco Escolano,et al.  Graph-Based Representations in Pattern Recognition, 6th IAPR-TC-15 International Workshop, GbRPR 2007, Alicante, Spain, June 11-13, 2007, Proceedings , 2007, GbRPR.

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

[4]  Harry Shum,et al.  Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement , 2011, IEEE Transactions on Image Processing.

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

[6]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  Yingli Tian,et al.  Single image super-resolution via internal gradient similarity , 2016, J. Vis. Commun. Image Represent..

[8]  Chi-Keung Tang,et al.  Fast image/video upsampling , 2008, SIGGRAPH 2008.

[9]  Chao Ren,et al.  Single image super resolution using local smoothness and nonlocal self-similarity priors , 2016, Signal Process. Image Commun..

[10]  Cordelia Schmid,et al.  A sparse texture representation using local affine regions , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Yangquan Chen,et al.  Single image super-resolution using self-optimizing mask via fractional-order gradient interpolation and reconstruction , 2017, ISA transactions.

[12]  Worthy N. Martin,et al.  Image Motion Estimation From Motion Smear-A New Computational Model , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Patrick Bouthemy,et al.  Space-Time Adaptation for Patch-Based Image Sequence Restoration , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[15]  Chih-Yuan Yang,et al.  Single-Image Super-Resolution: A Benchmark , 2014, ECCV.

[16]  Raanan Fattal Image upsampling via imposed edge statistics , 2007, SIGGRAPH 2007.

[17]  Yanning Zhang,et al.  Single Image Super-resolution Using Deformable Patches , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Jie Xu,et al.  Compressed multi-scale feature fusion network for single image super-resolution , 2018, Signal Process..

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

[20]  Yadong Wu,et al.  Single image super-resolution via blind blurring estimation and anchored space mapping , 2016, Computational Visual Media.

[21]  Zhixun Su,et al.  Kernel estimation from salient structure for robust motion deblurring , 2012, Signal Process. Image Commun..

[22]  Anat Levin,et al.  Accurate Blur Models vs. Image Priors in Single Image Super-resolution , 2013, 2013 IEEE International Conference on Computer Vision.

[23]  Xinbo Gao,et al.  Single image super-resolution using regularization of non-local steering kernel regression , 2016, Signal Process..

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

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

[26]  Daniel Cremers,et al.  An Improved Algorithm for TV-L 1 Optical Flow , 2009, Statistical and Geometrical Approaches to Visual Motion Analysis.

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

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

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

[30]  Sanjoy Dasgupta,et al.  Random projection trees and low dimensional manifolds , 2008, STOC.

[31]  Qi Wang,et al.  Example-based super-resolution via social images , 2016, Neurocomputing.

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

[33]  Yangquan Chen,et al.  Fractional calculus in image processing: a review , 2016, ArXiv.

[34]  Chih-Yuan Yang,et al.  Fast Direct Super-Resolution by Simple Functions , 2013, 2013 IEEE International Conference on Computer Vision.

[35]  K. R. Murali,et al.  Electrical and optical properties of pulse plated CdSxTe1-x films , 2010 .