Learning Super-Resolution Jointly From External and Internal Examples
Authors:
- 5 August 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 24 (11) , 4359-4371
Abstract
Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a low-resolution (LR) input. Image priors are commonly learned to regularize the, otherwise, seriously ill-posed SR problem, either using external LR-HR pairs or internal similar patterns. We propose joint SR to adaptively combine the advantages of both external and internal SR methods. We define two loss functions using sparse coding-based external examples, and epitomic matching based on internal examples, as well as a corresponding adaptive weight to automatically balance their contributions according to their reconstruction errors. Extensive SR results demonstrate the effectiveness of the proposed method over the existing state-of-the-art methods, and is also verified by our subjective evaluation study.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Combining the power of Internal and External denoising2013
- Learning How to Combine Internal and External Denoising Methods2013
- Nonlocally Centralized Sparse Representation for Image RestorationIEEE Transactions on Image Processing, 2012
- Internal statistics of a single natural image2011
- Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive RegularizationIEEE Transactions on Image Processing, 2011
- Image Super-Resolution Via Sparse RepresentationIEEE Transactions on Image Processing, 2010
- Is Denoising Dead?IEEE Transactions on Image Processing, 2009
- Super-resolution from a single image2009
- Non-local sparse models for image restoration2009
- Rank Analysis of Incomplete Block Designs: I. The Method of Paired ComparisonsBiometrika, 1952