Single-image rain removal using residual deep learning

Takuro Matsui, Takanori Fujisawa, Takuro Yamaguchi, Masaaki Ikehara

    研究成果: Conference contribution

    4 被引用数 (Scopus)

    抄録

    Most outdoor vision systems can be influenced by rainy weather conditions. In this paper, we address a rain removal problem from a single image. Some existing de-raining methods suffer from hue change due to neglect of the information in low frequency layer. Others fail in assuming enough rainy image models. To solve them, we propose a residual deep network architecture called ResDerainNet. Based on the deep convolutional neural network (CNN), we learn the mapping relationship between rainy and residual images from data. Furthermore, for training, we synthesize rainy images considering various rain models. Specifically, we mainly focus on the composite models as well as orientations and scales of rain streaks. The experiments demonstrate that our proposed model is applicable to a variety of images. Compared with state-of-the-art methods, our proposed method achieves better results on both synthetic and real-world images.

    本文言語English
    ホスト出版物のタイトル2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
    出版社IEEE Computer Society
    ページ3928-3932
    ページ数5
    ISBN(電子版)9781479970612
    DOI
    出版ステータスPublished - 2018 8 29
    イベント25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
    継続期間: 2018 10 72018 10 10

    出版物シリーズ

    名前Proceedings - International Conference on Image Processing, ICIP
    ISSN(印刷版)1522-4880

    Conference

    Conference25th IEEE International Conference on Image Processing, ICIP 2018
    国/地域Greece
    CityAthens
    Period18/10/718/10/10

    ASJC Scopus subject areas

    • ソフトウェア
    • コンピュータ ビジョンおよびパターン認識
    • 信号処理

    フィンガープリント

    「Single-image rain removal using residual deep learning」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