Fast image super-resolution via selective manifold learning of high-resolution patches

This paper considers the problem of single image super-resolution (SR). Previous example-based SR approaches mainly focus on analyzing the co-occurrence properties of low resolution (LR) and high resolution (HR) patches via dictionary learning. In our recent work [1], a novel approach (SR via sparse subspace clustering-based linear approximation of manifold or SLAM) has been proposed. In this paper, we further improve the SLAM method by considering and analyzing each tangent subspace as one point in a Grassmann manifold to select an optimal subset of tangent spaces. Furthermore, the optimal subset is clustered hierarchically, which helps in reducing the proposed algorithm's complexity significantly while still preserving the quality of the reconstructed HR image.

[1]  Chinh T. Dang,et al.  Key frame extraction from consumer videos using epitome , 2012, 2012 19th IEEE International Conference on Image Processing.

[2]  Mark Tygert,et al.  A Fast Randomized Algorithm for Orthogonal Projection , 2009, SIAM J. Sci. Comput..

[3]  Chun Qi,et al.  Low-Rank Neighbor Embedding for Single Image Super-Resolution , 2014, IEEE Signal Processing Letters.

[4]  Michael Elad,et al.  A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution , 2014, IEEE Transactions on Image Processing.

[5]  Quan Pan,et al.  Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Guillermo Sapiro,et al.  Non-local sparse models for image restoration , 2009, 2009 IEEE 12th International Conference on Computer Vision.

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

[8]  Gene H. Golub,et al.  Numerical methods for computing angles between linear subspaces , 1971, Milestones in Matrix Computation.

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

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

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

[12]  Chinh T. Dang,et al.  Single image super resolution via manifold linear approximation using sparse subspace clustering , 2013, 2013 IEEE Global Conference on Signal and Information Processing.

[13]  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..

[14]  Thomas S. Huang,et al.  Bilevel sparse coding for coupled feature spaces , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Xuelong Li,et al.  Learning Multiple Linear Mappings for Efficient Single Image Super-Resolution , 2015, IEEE Transactions on Image Processing.

[16]  Chi-Keung Tang,et al.  Fast image/video upsampling , 2008, SIGGRAPH Asia '08.

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

[18]  R. Vidal,et al.  Sparse Subspace Clustering: Algorithm, Theory, and Applications. , 2013, IEEE transactions on pattern analysis and machine intelligence.

[19]  Shiguang Shan,et al.  Aligning Coupled Manifolds for Face Hallucination , 2009, IEEE Signal Processing Letters.

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

[21]  Chinh T. Dang,et al.  Image Super-Resolution via Local Self-Learning Manifold Approximation , 2014, IEEE Signal Processing Letters.

[22]  René Vidal,et al.  Sparse Subspace Clustering: Algorithm, Theory, and Applications , 2012, IEEE transactions on pattern analysis and machine intelligence.

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

[24]  Chinh T. Dang,et al.  Heterogeneity Image Patch Index and Its Application to Consumer Video Summarization , 2014, IEEE Transactions on Image Processing.