Single image super-resolution reconstruction algorithm based on eage selection

Super-resolution (SR) has become more important, because it can generate high-quality high-resolution (HR) images from low-resolution (LR) input images. At present, there are a lot of work is concentrated on developing sophisticated image priors to improve the image quality, while taking much less attention to estimating and incorporating the blur model that can also impact the reconstruction results. We present a new reconstruction method based on eager selection. This method takes full account of the factors that affect the blur kernel estimation and accurately estimating the blur process. When comparing with the state-of-the-art methods, our method has comparable performance.

[1]  Stephen Lin,et al.  Super resolution using edge prior and single image detail synthesis , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

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

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

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

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

[8]  I. Bégin,et al.  Blind super-resolution using a learning-based approach , 2004, ICPR 2004.

[9]  Kwang In Kim,et al.  Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.