Single image super resolution based on multi-scale structural self similarity and neighborhood regression

Multi-scale structural self-similarity refer to those similar structures recurring many times within and across scales of the same image. In this paper, we present a single image super resolution (SR) method based on multi-scale structural selfsimilarity and neighborhood regression, which reconstructs a high resolution (HR) image from the image pyramid of the input image itself without depending on extrinsic set of training images. In the proposed approach, we find the nearest neighbor patches for each low resolution (LR) image patch, and then learn the neighborhood regression to map low resolution space to high resolution space. Experimental results show that our approach acquires better result in peak signal to noise ratio and visual effects against several competing methods.

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

[2]  Guangtao Zhai,et al.  Single Image Super-resolution With Detail Enhancement Based on Local Fractal Analysis of Gradient , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

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

[4]  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.

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

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

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

[8]  Gaofeng Meng,et al.  Edge-Directed Single-Image Super-Resolution Via Adaptive Gradient Magnitude Self-Interpolation , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Narendra Ahuja,et al.  Single image super-resolution from transformed self-exemplars , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Xuelong Li,et al.  Single Image Super-Resolution With Multiscale Similarity Learning , 2013, IEEE Transactions on Neural Networks and Learning Systems.

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

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

[13]  D. Yeung,et al.  Super-resolution through neighbor embedding , 2004, CVPR 2004.