A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution
Top Cited Papers
- 19 February 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (6), 2569-2582
- https://doi.org/10.1109/tip.2014.2305844
Abstract
We address single image super-resolution using a statistical prediction model based on sparse representations of low- and high-resolution image patches. The suggested model allows us to avoid any invariance assumption, which is a common practice in sparsity-based approaches treating this task. Prediction of high resolution patches is obtained via MMSE estimation and the resulting scheme has the useful interpretation of a feedforward neural network. To further enhance performance, we suggest data clustering and cascading several levels of the basic algorithm. We suggest a training scheme for the resulting network and demonstrate the capabilities of our algorithm, showing its advantages over existing methods based on a low- and high-resolution dictionary pair, in terms of computational complexity, numerical criteria, and visual appearance. The suggested approach offers a desirable compromise between low computational complexity and reconstruction quality, when comparing it with state-of-the-art methods for single image super-resolution.Keywords
Funding Information
- European Research Council under EU's 7th Framework Program
- ERC (320649)
- Intel Collaborative Research Institute for Computational Intelligence
This publication has 28 references indexed in Scilit:
- Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-ResolutionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Image and video upscaling from local self-examplesACM Transactions on Graphics, 2011
- From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and ImagesSIAM Review, 2009
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Bayesian Variable Selection and Regularization for Time–Frequency Surface EstimationJournal of the Royal Statistical Society Series B: Statistical Methodology, 2004
- Advances and challenges in super‐resolutionInternational Journal of Imaging Systems and Technology, 2004
- Super-resolution image reconstruction: a technical overviewIEEE Signal Processing Magazine, 2003
- Orthogonal matching pursuit: recursive function approximation with applications to wavelet decompositionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002