The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
À mesure que la résolution d’affichage augmente, une technique efficace de mise à l’échelle de l’image est nécessaire pour les écrans récents tels qu’un écran ultra haute définition. Même si divers algorithmes de super-résolution d’image ont été développés pour la mise à l’échelle de l’image, ils n’offrent toujours pas les excellentes performances de l’affichage ultra haute définition. En effet, la capacité de création de texture des algorithmes n'est pas suffisante. Par conséquent, cet article propose un algorithme de création de texture efficace pour améliorer les performances de super-résolution des textures. Pour la création de textures, nous construisons une base de données avec des patchs aléatoires lors du traitement hors ligne, puis nous synthétisons des textures fines en utilisant un filtre guidé dans le traitement en temps réel en ligne, basé sur la base de données. Les résultats expérimentaux montrent que l'algorithme de création de texture proposé fournit des textures plus nettes et plus fines par rapport aux algorithmes de pointe existants.
Seok Bong YOO
Electronics and Telecommunications Research Institute (ETRI)
Mikyong HAN
Electronics and Telecommunications Research Institute (ETRI)
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.
Copier
Seok Bong YOO, Mikyong HAN, "Efficient Texture Creation Based on Random Patches in Database and Guided Filter" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 11, pp. 2840-2843, November 2018, doi: 10.1587/transinf.2018EDL8143.
Abstract: As the display resolution increases, an effective image upscaling technique is required for recent displays such as an ultra-high-definition display. Even though various image super-resolution algorithms have been developed for the image upscaling, they still do not provide the excellent performance in the ultra-high-definition display. This is because the texture creation capability in the algorithms is not sufficient. Hence, this paper proposes an efficient texture creation algorithm for enhancing the texture super-resolution performance. For the texture creation, we build a database with random patches in the off-line processing and we then synthesize fine textures by employing guided filter in the on-line real-time processing, based on the database. Experimental results show that the proposed texture creation algorithm provides sharper and finer textures compared with the existing state-of-the-art algorithms.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8143/_p
Copier
@ARTICLE{e101-d_11_2840,
author={Seok Bong YOO, Mikyong HAN, },
journal={IEICE TRANSACTIONS on Information},
title={Efficient Texture Creation Based on Random Patches in Database and Guided Filter},
year={2018},
volume={E101-D},
number={11},
pages={2840-2843},
abstract={As the display resolution increases, an effective image upscaling technique is required for recent displays such as an ultra-high-definition display. Even though various image super-resolution algorithms have been developed for the image upscaling, they still do not provide the excellent performance in the ultra-high-definition display. This is because the texture creation capability in the algorithms is not sufficient. Hence, this paper proposes an efficient texture creation algorithm for enhancing the texture super-resolution performance. For the texture creation, we build a database with random patches in the off-line processing and we then synthesize fine textures by employing guided filter in the on-line real-time processing, based on the database. Experimental results show that the proposed texture creation algorithm provides sharper and finer textures compared with the existing state-of-the-art algorithms.},
keywords={},
doi={10.1587/transinf.2018EDL8143},
ISSN={1745-1361},
month={November},}
Copier
TY - JOUR
TI - Efficient Texture Creation Based on Random Patches in Database and Guided Filter
T2 - IEICE TRANSACTIONS on Information
SP - 2840
EP - 2843
AU - Seok Bong YOO
AU - Mikyong HAN
PY - 2018
DO - 10.1587/transinf.2018EDL8143
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2018
AB - As the display resolution increases, an effective image upscaling technique is required for recent displays such as an ultra-high-definition display. Even though various image super-resolution algorithms have been developed for the image upscaling, they still do not provide the excellent performance in the ultra-high-definition display. This is because the texture creation capability in the algorithms is not sufficient. Hence, this paper proposes an efficient texture creation algorithm for enhancing the texture super-resolution performance. For the texture creation, we build a database with random patches in the off-line processing and we then synthesize fine textures by employing guided filter in the on-line real-time processing, based on the database. Experimental results show that the proposed texture creation algorithm provides sharper and finer textures compared with the existing state-of-the-art algorithms.
ER -