Pixel and Patch Reordering for Fast Patch Selection in Exemplar-Based Image Inpainting
Summary :
This letter presents a scheme to improve the running time of exemplar-based image inpainting, first proposed by Criminisi et al. In the exemplar-based image inpainting, a patch that contains unknown pixels is compared to all the patches in the known region in order to find the best match. This is very time-consuming and hinders the practicality of Criminisi's method to be used in real time. We show that a simple bounding algorithm can significantly reduce number of distance calculations, and thus the running time. Performance of the bounding algorithm is affected by the order of patches that are compared, as well as the order of pixels in a patch. We present pixel and patch ordering schemes that improve the performance of bounding algorithms. Experiments with well-known images used in inpainting literature show that the proposed reordering scheme can reduce running time of the bounding algorithm up to 50%.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.12 pp.2892-2895
- Publication Date
- 2013/12/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.2892
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Baeksop KIM
Hallym University
Jiseong KIM
Hallym University
Jungmin SO
Hallym 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
Baeksop KIM, Jiseong KIM, Jungmin SO, "Pixel and Patch Reordering for Fast Patch Selection in Exemplar-Based Image Inpainting" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 12, pp. 2892-2895, December 2013, doi: 10.1587/transinf.E96.D.2892.
Abstract: This letter presents a scheme to improve the running time of exemplar-based image inpainting, first proposed by Criminisi et al. In the exemplar-based image inpainting, a patch that contains unknown pixels is compared to all the patches in the known region in order to find the best match. This is very time-consuming and hinders the practicality of Criminisi's method to be used in real time. We show that a simple bounding algorithm can significantly reduce number of distance calculations, and thus the running time. Performance of the bounding algorithm is affected by the order of patches that are compared, as well as the order of pixels in a patch. We present pixel and patch ordering schemes that improve the performance of bounding algorithms. Experiments with well-known images used in inpainting literature show that the proposed reordering scheme can reduce running time of the bounding algorithm up to 50%.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2892/_p
Copy
@ARTICLE{e96-d_12_2892,
author={Baeksop KIM, Jiseong KIM, Jungmin SO, },
journal={IEICE TRANSACTIONS on Information},
title={Pixel and Patch Reordering for Fast Patch Selection in Exemplar-Based Image Inpainting},
year={2013},
volume={E96-D},
number={12},
pages={2892-2895},
abstract={This letter presents a scheme to improve the running time of exemplar-based image inpainting, first proposed by Criminisi et al. In the exemplar-based image inpainting, a patch that contains unknown pixels is compared to all the patches in the known region in order to find the best match. This is very time-consuming and hinders the practicality of Criminisi's method to be used in real time. We show that a simple bounding algorithm can significantly reduce number of distance calculations, and thus the running time. Performance of the bounding algorithm is affected by the order of patches that are compared, as well as the order of pixels in a patch. We present pixel and patch ordering schemes that improve the performance of bounding algorithms. Experiments with well-known images used in inpainting literature show that the proposed reordering scheme can reduce running time of the bounding algorithm up to 50%.},
keywords={},
doi={10.1587/transinf.E96.D.2892},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Pixel and Patch Reordering for Fast Patch Selection in Exemplar-Based Image Inpainting
T2 - IEICE TRANSACTIONS on Information
SP - 2892
EP - 2895
AU - Baeksop KIM
AU - Jiseong KIM
AU - Jungmin SO
PY - 2013
DO - 10.1587/transinf.E96.D.2892
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2013
AB - This letter presents a scheme to improve the running time of exemplar-based image inpainting, first proposed by Criminisi et al. In the exemplar-based image inpainting, a patch that contains unknown pixels is compared to all the patches in the known region in order to find the best match. This is very time-consuming and hinders the practicality of Criminisi's method to be used in real time. We show that a simple bounding algorithm can significantly reduce number of distance calculations, and thus the running time. Performance of the bounding algorithm is affected by the order of patches that are compared, as well as the order of pixels in a patch. We present pixel and patch ordering schemes that improve the performance of bounding algorithms. Experiments with well-known images used in inpainting literature show that the proposed reordering scheme can reduce running time of the bounding algorithm up to 50%.
ER -
English
