Exploration into Single Image Super-Resolution via Self Similarity by Sparse Representation
Summary :
A novel method for single image super resolution without any training samples is presented in the paper. By sparse representation, the method attempts to recover at each pixel its best possible resolution increase based on the self similarity of the image patches across different scale and rotation transforms. The experiments indicate that the proposed method can produce robust and competitive results.
- Publication
- IEICE TRANSACTIONS on Information Vol.E93-D No.11 pp.3144-3148
- Publication Date
- 2010/11/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E93.D.3144
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Lv GUO, Yin LI, Jie YANG, Li LU, "Exploration into Single Image Super-Resolution via Self Similarity by Sparse Representation" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 11, pp. 3144-3148, November 2010, doi: 10.1587/transinf.E93.D.3144.
Abstract: A novel method for single image super resolution without any training samples is presented in the paper. By sparse representation, the method attempts to recover at each pixel its best possible resolution increase based on the self similarity of the image patches across different scale and rotation transforms. The experiments indicate that the proposed method can produce robust and competitive results.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.3144/_p
Copy
@ARTICLE{e93-d_11_3144,
author={Lv GUO, Yin LI, Jie YANG, Li LU, },
journal={IEICE TRANSACTIONS on Information},
title={Exploration into Single Image Super-Resolution via Self Similarity by Sparse Representation},
year={2010},
volume={E93-D},
number={11},
pages={3144-3148},
abstract={A novel method for single image super resolution without any training samples is presented in the paper. By sparse representation, the method attempts to recover at each pixel its best possible resolution increase based on the self similarity of the image patches across different scale and rotation transforms. The experiments indicate that the proposed method can produce robust and competitive results.},
keywords={},
doi={10.1587/transinf.E93.D.3144},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Exploration into Single Image Super-Resolution via Self Similarity by Sparse Representation
T2 - IEICE TRANSACTIONS on Information
SP - 3144
EP - 3148
AU - Lv GUO
AU - Yin LI
AU - Jie YANG
AU - Li LU
PY - 2010
DO - 10.1587/transinf.E93.D.3144
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2010
AB - A novel method for single image super resolution without any training samples is presented in the paper. By sparse representation, the method attempts to recover at each pixel its best possible resolution increase based on the self similarity of the image patches across different scale and rotation transforms. The experiments indicate that the proposed method can produce robust and competitive results.
ER -
English
