Single image super-resolution with limited number of filters

Yusuke Nakahara, Takuro Yamaguchi, Masaaki Ikehara

    研究成果: Conference contribution

    1 被引用数 (Scopus)

    抄録

    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 sucient 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.

    本文言語English
    ホスト出版物のタイトル2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ36-40
    ページ数5
    ISBN(電子版)9781728112954
    DOI
    出版ステータスPublished - 2019 2 20
    イベント2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Anaheim, United States
    継続期間: 2018 11 262018 11 29

    出版物シリーズ

    名前2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

    Conference

    Conference2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018
    国/地域United States
    CityAnaheim
    Period18/11/2618/11/29

    ASJC Scopus subject areas

    • 情報システム
    • 信号処理

    フィンガープリント

    「Single image super-resolution with limited number of filters」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル