講演抄録/キーワード |
講演名 |
2018-06-29 09:55
Single Image Super-Resolution with Limited Number of Filters ○Yusuke Nakahara・Takuro Yamaguchi・Masaaki Ikehara(Keio Univ.) IE2018-22 |
抄録 |
(和) |
In this paper, we propose a single image super-resolution with limited number of filters based on RAISR. RAISR is well known as rapid and accurate super-resolution method which utilizes 864 filters for upscaling. This super-resolution idea utilizes the filter learned with sufficient training set. To get low cost of calculation and comparable image quality with other highly accurate super-resolution methods, the patch of input image is classified into classes by simple hash calculation. Then, the high quality version of this patch is generated by applying the filter to low resolution patches. In our method, only 18 filters can make high resolution images by using simple geometric conversion and rotation conversion while keeping the accuracy and runtime of RAISR. |
(英) |
In this paper, we propose a single image super-resolution with limited number of filters based on RAISR. RAISR is well known as rapid and accurate super-resolution method which utilizes 864 filters for upscaling. This super-resolution idea utilizes the filter learned with sufficient training set. To get low cost of calculation and comparable image quality with other highly accurate super-resolution methods, the patch of input image is classified into classes by simple hash calculation. Then, the high quality version of this patch is generated by applying the filter to low resolution patches. In our method, only 18 filters can make high resolution images by using simple geometric conversion and rotation conversion while keeping the accuracy and runtime of RAISR. |
キーワード |
(和) |
超解像 / 画像強調 / フィルタ学習 / / / / / |
(英) |
super-resolution / image enhancement / filter learning / / / / / |
文献情報 |
信学技報, vol. 118, no. 113, IE2018-22, pp. 7-11, 2018年6月. |
資料番号 |
IE2018-22 |
発行日 |
2018-06-22 (IE) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
IE2018-22 |