Fast Search of a Similar Patch for Self-Similarity Based Image Super Resolution
Summary :
In the self-similarity super resolution (SR) approach, similar examples are searched across down-scales in the image pyramid, and the computations of searching similar examples are very heavy. This makes it difficult to work in a real-time way under common software implementation. Therefore, the search process should be further accelerated at an algorithm level. Cauchy-Schwarz inequality has been used previously for fast vector quantization (VQ) encoding. The candidate patches in the search region of SR are analogous to the code-words in the VQ, and Cauchy-Schwarz inequality is exploited to exclude implausible candidate patches early. Consequently, significant acceleration of the similar patch search process is achieved. The proposed method can easily make an optimal trade-off between running speed and visual quality by appropriately configuring the bypass-threshold.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.8 pp.2194-2198
- Publication Date
- 2016/08/01
- Publicized
- 2016/05/16
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2016EDL8049
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Jun-Sang YOO
Korea University
Ji-Hoon CHOI
Korea University
Kang-Sun CHOI
Koreatech
Dae-Yeol LEE
Electronics and Telecommunications Research Institute (ETRI)
Hui-Yong KIM
Electronics and Telecommunications Research Institute (ETRI)
Jong-Ok KIM
Korea University
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
Jun-Sang YOO, Ji-Hoon CHOI, Kang-Sun CHOI, Dae-Yeol LEE, Hui-Yong KIM, Jong-Ok KIM, "Fast Search of a Similar Patch for Self-Similarity Based Image Super Resolution" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 8, pp. 2194-2198, August 2016, doi: 10.1587/transinf.2016EDL8049.
Abstract: In the self-similarity super resolution (SR) approach, similar examples are searched across down-scales in the image pyramid, and the computations of searching similar examples are very heavy. This makes it difficult to work in a real-time way under common software implementation. Therefore, the search process should be further accelerated at an algorithm level. Cauchy-Schwarz inequality has been used previously for fast vector quantization (VQ) encoding. The candidate patches in the search region of SR are analogous to the code-words in the VQ, and Cauchy-Schwarz inequality is exploited to exclude implausible candidate patches early. Consequently, significant acceleration of the similar patch search process is achieved. The proposed method can easily make an optimal trade-off between running speed and visual quality by appropriately configuring the bypass-threshold.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8049/_p
Copy
@ARTICLE{e99-d_8_2194,
author={Jun-Sang YOO, Ji-Hoon CHOI, Kang-Sun CHOI, Dae-Yeol LEE, Hui-Yong KIM, Jong-Ok KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Fast Search of a Similar Patch for Self-Similarity Based Image Super Resolution},
year={2016},
volume={E99-D},
number={8},
pages={2194-2198},
abstract={In the self-similarity super resolution (SR) approach, similar examples are searched across down-scales in the image pyramid, and the computations of searching similar examples are very heavy. This makes it difficult to work in a real-time way under common software implementation. Therefore, the search process should be further accelerated at an algorithm level. Cauchy-Schwarz inequality has been used previously for fast vector quantization (VQ) encoding. The candidate patches in the search region of SR are analogous to the code-words in the VQ, and Cauchy-Schwarz inequality is exploited to exclude implausible candidate patches early. Consequently, significant acceleration of the similar patch search process is achieved. The proposed method can easily make an optimal trade-off between running speed and visual quality by appropriately configuring the bypass-threshold.},
keywords={},
doi={10.1587/transinf.2016EDL8049},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - Fast Search of a Similar Patch for Self-Similarity Based Image Super Resolution
T2 - IEICE TRANSACTIONS on Information
SP - 2194
EP - 2198
AU - Jun-Sang YOO
AU - Ji-Hoon CHOI
AU - Kang-Sun CHOI
AU - Dae-Yeol LEE
AU - Hui-Yong KIM
AU - Jong-Ok KIM
PY - 2016
DO - 10.1587/transinf.2016EDL8049
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2016
AB - In the self-similarity super resolution (SR) approach, similar examples are searched across down-scales in the image pyramid, and the computations of searching similar examples are very heavy. This makes it difficult to work in a real-time way under common software implementation. Therefore, the search process should be further accelerated at an algorithm level. Cauchy-Schwarz inequality has been used previously for fast vector quantization (VQ) encoding. The candidate patches in the search region of SR are analogous to the code-words in the VQ, and Cauchy-Schwarz inequality is exploited to exclude implausible candidate patches early. Consequently, significant acceleration of the similar patch search process is achieved. The proposed method can easily make an optimal trade-off between running speed and visual quality by appropriately configuring the bypass-threshold.
ER -
English
