Soft Edge Smoothness Prior for Alpha Channel Super Resolution

Effective image prior is necessary for image super resolution, due to its severely under-determined nature. Although the edge smoothness prior can be effective, it is generally difficult to have analytical forms to evaluate the edge smoothness, especially for soft edges that exhibit gradual intensity transitions. This paper finds the connection between the soft edge smoothness and a soft cut metric on an image grid by generalizing the Geocuts method (Y. Boykov and V. Kolmogorov, 2003), and proves that the soft edge smoothness measure approximates the average length of all level lines in an intensity image. This new finding not only leads to an analytical characterization of the soft edge smoothness prior, but also gives an intuitive geometric explanation. Regularizing the super resolution problem by this new form of prior can simultaneously minimize the length of all level lines, and thus resulting in visually appealing results. In addition, this paper presents a novel combination of this soft edge smoothness prior and the alpha matting technique for color image super resolution, by normalizing edge segments with their alpha channel description, to achieve a unified treatment of edges with different contrast and scale.

[1]  Thomas S. Huang,et al.  Image processing , 1971 .

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

[3]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[4]  Ping Wah Wong,et al.  Edge-directed interpolation , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[5]  Michael Elad,et al.  Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images , 1997, IEEE Trans. Image Process..

[6]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[7]  Anil K. Jain,et al.  Learning 2D shape models , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[9]  Bryan S. Morse,et al.  Image magnification using level-set reconstruction , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  M. Orchard,et al.  New edge-directed interpolation , 2001, IEEE Trans. Image Process..

[11]  Harry Shum,et al.  A two-step approach to hallucinating faces: global parametric model and local nonparametric model , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[12]  Tony F. Chan,et al.  The digital TV filter and nonlinear denoising , 2001, IEEE Trans. Image Process..

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

[14]  Andrew Blake,et al.  Super-resolution Enhancement of Video , 2003, AISTATS.

[15]  Vladimir Kolmogorov,et al.  Computing geodesics and minimal surfaces via graph cuts , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[16]  Bryan C. Russell,et al.  Exploiting the sparse derivative prior for super-resolution , 2003 .

[17]  Nanning Zheng,et al.  Image hallucination with primal sketch priors , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[18]  N. H. C. Yung,et al.  Curvature scale space corner detector with adaptive threshold and dynamic region of support , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[19]  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..

[20]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Michael Elad,et al.  Fast and robust multiframe super resolution , 2004, IEEE Transactions on Image Processing.

[22]  Heung-Yeung Shum,et al.  Fundamental limits of reconstruction-based superresolution algorithms under local translation , 2004 .

[23]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  William T. Freeman,et al.  Learning Low-Level Vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[25]  Serge J. Belongie,et al.  Big Little Icons , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[26]  Harry Shum,et al.  Patch based blind image super resolution , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[27]  Frédéric Champagnat,et al.  Continuous Super-Resolution for Recovery of 1-D Image Features: Algorithm and Performance Modeling , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[28]  Michael Elad,et al.  Multiframe demosaicing and super-resolution of color images , 2006, IEEE Transactions on Image Processing.

[29]  Chi-Keung Tang,et al.  Perceptually-Inspired and Edge-Directed Color Image Super-Resolution , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[30]  Richard Szeliski,et al.  Video and Image Bayesian Demosaicing with a Two Color Image Prior , 2006, ECCV.

[31]  Mei Han,et al.  Video Super-resolution with Scene-specific Priors , 2006, BMVC.

[32]  Aggelos K. Katsaggelos,et al.  Super Resolution of Images and Video , 2006, Super Resolution of Images and Video.

[33]  Dani Lischinski,et al.  A Closed-Form Solution to Natural Image Matting , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.