Single Image Super Resolution Using Joint Regularization

This letter proposes a reconstruction-based single image super resolution method by using joint regularization, where a group-residual-based regularization (GRR) and a ridge-regression-based regularization (3R) are combined. In GRR, nonlocal similar patches are grouped together, and the group weights are calculated so as to adaptively constrain the residual values in the gradient domain. In 3R, we adopt the ridge-regression-based method to establish the projection matrices from an external high-resolution (HR) training set, so that the external HR information can be utilized. To obtain an estimation of the targeted HR image, an efficient algorithm is designed for solving the joint formulation. Experimental results on different image datasets indicate that the proposed method is able to achieve the state-of-the-art performance.

[1]  Jean-Michel Morel,et al.  A Review of Image Denoising Algorithms, with a New One , 2005, Multiscale Model. Simul..

[2]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

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

[4]  Lei Zhang,et al.  Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization , 2010, IEEE Transactions on Image Processing.

[5]  Jean-François Aujol,et al.  Image Zoom Completion , 2016, IEEE Transactions on Image Processing.

[6]  Thomas S. Huang,et al.  Deep Networks for Image Super-Resolution with Sparse Prior , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Thomas S. Huang,et al.  Learning Super-Resolution Jointly From External and Internal Examples , 2015, IEEE Transactions on Image Processing.

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

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

[10]  Xinfeng Zhang,et al.  Retrieval Compensated Group Structured Sparsity for Image Super-Resolution , 2017, IEEE Transactions on Multimedia.

[11]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[12]  Guy Gilboa,et al.  Nonlocal Operators with Applications to Image Processing , 2008, Multiscale Model. Simul..

[13]  Petros Maragos,et al.  Structure Tensor Total Variation , 2015, SIAM J. Imaging Sci..

[14]  Baoxin Li,et al.  Compressive Sensing Reconstruction of Correlated Images Using Joint Regularization , 2016, IEEE Signal Processing Letters.

[15]  Truong Q. Nguyen,et al.  Single Image Super-Resolution Using Local Geometric Duality and Non-Local Similarity , 2016, IEEE Transactions on Image Processing.

[16]  Yu-Chiang Frank Wang,et al.  A Self-Learning Approach to Single Image Super-Resolution , 2013, IEEE Transactions on Multimedia.

[17]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

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

[19]  Jean-François Aujol,et al.  Texture Reconstruction Guided by a High-Resolution Patch , 2017, IEEE Transactions on Image Processing.

[20]  Mathews Jacob,et al.  Higher Degree Total Variation (HDTV) Regularization for Image Recovery , 2012, IEEE Transactions on Image Processing.

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

[22]  Xuelong Li,et al.  Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression , 2012, IEEE Transactions on Image Processing.

[23]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

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

[25]  Junjun Jiang,et al.  Single Image Super-Resolution via Locally Regularized Anchored Neighborhood Regression and Nonlocal Means , 2017, IEEE Transactions on Multimedia.

[26]  Xiaoou Tang,et al.  Accelerating the Super-Resolution Convolutional Neural Network , 2016, ECCV.

[27]  Karl Kunisch,et al.  Total Generalized Variation , 2010, SIAM J. Imaging Sci..

[28]  Baoxin Li,et al.  Understanding Compressive Sensing and Sparse Representation-Based Super-Resolution , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[29]  Xuelong Li,et al.  Image Super-Resolution With Sparse Neighbor Embedding , 2012, IEEE Transactions on Image Processing.

[30]  Truong Q. Nguyen,et al.  Single Image Super-Resolution via Adaptive High-Dimensional Non-Local Total Variation and Adaptive Geometric Feature , 2017, IEEE Transactions on Image Processing.

[31]  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.

[32]  Jean-François Aujol,et al.  Super-resolution from a low- and partial high-resolution image pair , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[33]  Karen O. Egiazarian,et al.  Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction , 2013, IEEE Transactions on Image Processing.

[34]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  In Kyu Park,et al.  Deep CNN-Based Super-Resolution Using External and Internal Examples , 2017, IEEE Signal Processing Letters.

[36]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Nelly Pustelnik,et al.  A Nonlocal Structure Tensor-Based Approach for Multicomponent Image Recovery Problems , 2014, IEEE Transactions on Image Processing.

[38]  Xavier Bresson,et al.  Bregmanized Nonlocal Regularization for Deconvolution and Sparse Reconstruction , 2010, SIAM J. Imaging Sci..

[39]  Lei Zhang,et al.  Nonlocally Centralized Sparse Representation for Image Restoration , 2013, IEEE Transactions on Image Processing.

[40]  Guangming Shi,et al.  Compressive Sensing via Nonlocal Low-Rank Regularization , 2014, IEEE Transactions on Image Processing.

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

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

[43]  Peyman Milanfar,et al.  Kernel Regression for Image Processing and Reconstruction , 2007, IEEE Transactions on Image Processing.

[44]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[45]  Xiaohai He,et al.  Single Image Super-Resolution via Adaptive Transform-Based Nonlocal Self-Similarity Modeling and Learning-Based Gradient Regularization , 2017, IEEE Transactions on Multimedia.

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

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