Learning Super-Resolution Jointly from External and Internal Examples
Preprint
Abstract
Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a lowresolution (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 13 references indexed in Scilit:
- Nonlocally Centralized Sparse Representation for Image RestorationIEEE Transactions on Image Processing, 2012
- Coupled Dictionary Training for Image Super-ResolutionIEEE Transactions on Image Processing, 2012
- 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
- Single-Image Super-Resolution Using Sparse Regression and Natural Image PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Is Denoising Dead?IEEE Transactions on Image Processing, 2009
- Epitomic Location RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Fundamental limits of reconstruction-based superresolution algorithms under local translationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Super-resolution image reconstruction: a technical overviewIEEE Signal Processing Magazine, 2003
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002