Construction Method of Efficient Database for Learning-Based Video Super-Resolution

• Item type: Trans(1)
• 公開日: 2009-12-14
• タイトル: Construction Method of Efficient Database for Learning-Based Video Super-Resolution
• タイトル / 言語: en
• タイトル: Construction Method of Efficient Database for Learning-Based Video Super-Resolution
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: Regular Paper - Research Paper
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Advanced Technology R&D Center, Mitsubishi Electric Corporation
• 著者所属: Graduate School of Engineering Science, Osaka University
• 著者所属: Advanced Technology R&D Center, Mitsubishi Electric Corporation
• 著者所属: Advanced Technology R&D Center, Mitsubishi Electric Corporation
• 著者所属: Faculty of Information Science and Technology, Osaka Institute of Technology
• 著者所属(英): en
• 著者所属(英): Advanced Technology R&D Center, Mitsubishi Electric Corporation
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering Science, Osaka University
• 著者所属(英): en
• 著者所属(英): Advanced Technology R&D Center, Mitsubishi Electric Corporation
• 著者所属(英): en
• 著者所属(英): Advanced Technology R&D Center, Mitsubishi Electric Corporation
• 著者所属(英): en
• 著者所属(英): Faculty of Information Science and Technology, Osaka Institute of Technology
• 著者名: Kiyotaka, Watanabe; Yoshio, Iwai; Tetsuji, Haga; Koichi, Takeuchi; Masahiko, Yachida
• 著者名(英): Kiyotaka, Watanabe; Yoshio, Iwai; Tetsuji, Haga; Koichi, Takeuchi; Masahiko, Yachida
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: There are two major problems with learning-based super-resolution algorithms. One is that they require a large amount of memory to store examples; while the other is the high computational cost of finding the nearest neighbors in the database. In order to alleviate these problems, it is helpful to reduce the dimensionality of examples and to store only a small number of examples that contribute to the synthesis of a high quality video. Based on these ideas, we have developed an efficient algorithm for learning-based video super-resolution. We introduce several strategies to construct an efficient database. Through the evaluation experiments we show the efficiency of our approach in improving super-resolution algorithms.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: There are two major problems with learning-based super-resolution algorithms. One is that they require a large amount of memory to store examples; while the other is the high computational cost of finding the nearest neighbors in the database. In order to alleviate these problems, it is helpful to reduce the dimensionality of examples and to store only a small number of examples that contribute to the synthesis of a high quality video. Based on these ideas, we have developed an efficient algorithm for learning-based video super-resolution. We introduce several strategies to construct an efficient database. Through the evaluation experiments we show the efficiency of our approach in improving super-resolution algorithms.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12394973
• 書誌情報: IPSJ Transactions on Computer Vision and Applications（CVA）; 巻 1, p. 277-287, 発行日 2009-12-14
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-6695
• 出版者 / 言語: ja
• 出版者: 情報処理学会