Deep Inverse Tone Mapping Optimized for High Dynamic Range Display

Katsuhiko Hirao, Zhengxue Cheng, Masaru Takeuchi, Jiro Katto

    研究成果: Conference contribution

    1 被引用数 (Scopus)

    抄録

    The popularity of high dynamic range (HDR) makes the inverse tone mapping become an important technique for HDR display. In this paper, we propose a convolutional neural network (CNN) based inverse tone mapping method to generate a high-quality HDR image from one single standard dynamic range (SDR) image. First, we present a CNN design with a three-channel input, which considers both luminance and chrominance. Second, we propose to use overlapped inputs to remove the boundary artifacts, caused by zero padding in CNN. Experimental results demonstrate the high quality of our generated HDR images compared to the ground truth and conventional inverse tone mapping methods.

    本文言語English
    ホスト出版物のタイトル9th International Conference on Information and Communication Technology Convergence
    ホスト出版物のサブタイトルICT Convergence Powered by Smart Intelligence, ICTC 2018
    出版社Institute of Electrical and Electronics Engineers Inc.
    ページ472-474
    ページ数3
    ISBN(電子版)9781538650400
    DOI
    出版ステータスPublished - 2018 11 16
    イベント9th International Conference on Information and Communication Technology Convergence, ICTC 2018 - Jeju Island, Korea, Republic of
    継続期間: 2018 10 172018 10 19

    Other

    Other9th International Conference on Information and Communication Technology Convergence, ICTC 2018
    国/地域Korea, Republic of
    CityJeju Island
    Period18/10/1718/10/19

    ASJC Scopus subject areas

    • コンピュータ ネットワークおよび通信
    • コンピュータ サイエンスの応用
    • 情報システム
    • 情報システムおよび情報管理
    • 人工知能

    フィンガープリント

    「Deep Inverse Tone Mapping Optimized for High Dynamic Range Display」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