A study of norms in convex optimization super-resolution from compressed sources

Advancements over the last decade in video acquisition and display technologies lead to a continuous increase of video content resolution. These aspects combined with the shift towards cloud multimedia services and the underway adoption of High Efficiency Video Coding standards (HEVC) create a lot of interest for Super-Resolution (SR) and video enhancing techniques. Recent works showed that proximal based convex optimization approaches provide a promising direction in video restoration. An important aspect in the definition of a SR model is the metric used in defining the objective function. Most techniques are based on the classical I2 norm. In this paper we further investigate the use of other norms and their behavior w.r.t. multiple quality evaluation metrics. We show that significant gains of up to 0.5 dB can be obtained when using different norms.

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

[2]  Aline Roumy,et al.  Single-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples , 2014, IEEE Transactions on Image Processing.

[3]  J. Moreau.  Proximité et dualité dans un espace hilbertien , 1965 .

[4]  Patrick L. Combettes,et al.  Proximal Splitting Methods in Signal Processing , 2009, Fixed-Point Algorithms for Inverse Problems in Science and Engineering.

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

[6]  Cyril Bergeron,et al.  A Convex Optimization Framework for Video Quality and Resolution Enhancement From Multiple Descriptions , 2019, IEEE Transactions on Image Processing.

[7]  Frédéric Dufaux,et al.  Super-resolution of HEVC videos via convex optimization , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[8]  Valérie R. Wajs,et al.  A variational formulation for frame-based inverse problems , 2007 .

[9]  Aggelos K. Katsaggelos,et al.  Variational Bayesian Super Resolution , 2011, IEEE Transactions on Image Processing.

[10]  Aggelos K. Katsaggelos,et al.  Bayesian combination of sparse and non-sparse priors in image super resolution , 2013, Digit. Signal Process..

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

[12]  Caroline Chaux,et al.  A convex optimization approach for image resolution enhancement from compressed representations , 2013, 2013 18th International Conference on Digital Signal Processing (DSP).

[13]  R. Keys.  Cubic convolution interpolation for digital image processing , 1981 .

[14]  Aggelos K. Katsaggelos,et al.  A non-stationary image prior combination in super-resolution , 2014, Digit. Signal Process..

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

[16]  Ken Turkowski,et al.  Filters for common resampling tasks , 1990 .

[17]  Aggelos K. Katsaggelos,et al.  Super-resolution of compressed videos using convolutional neural networks , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[18]  P. L. Combettes,et al.  Primal-Dual Splitting Algorithm for Solving Inclusions with Mixtures of Composite, Lipschitzian, and Parallel-Sum Type Monotone Operators , 2011, Set-Valued and Variational Analysis.

[19]  Gary J. Sullivan,et al.  Overview of the High Efficiency Video Coding (HEVC) Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

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