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

• Watanabe Kiyotaka

  Advanced Technology R&D Center, Mitsubishi Electric Corporation

• Iwai Yoshio

  Graduate School of Engineering Science, Osaka University

• Haga Tetsuji

  Advanced Technology R&D Center, Mitsubishi Electric Corporation

• Takeuchi Koichi

  Advanced Technology R&D Center, Mitsubishi Electric Corporation

• Yachida Masahiko

  Faculty of Information Science and Technology, Osaka Institute of Technology

Abstract

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.

Journal

• IPSJ Transactions on Computer Vision and Applications

  IPSJ Transactions on Computer Vision and Applications 1 277-287, 2009

  Information Processing Society of Japan

Keywords

• Computer Vision and Pattern Recognition

Details

• CRID: 1390282680268757504
• NII Article ID: 130000142315
• NII Book ID: AN00116647
• ISSN: 18827772
• ISSN: 18826695
• ISSN: 03875806
• DOI: 10.2197/ipsjtcva.1.277
• NDL BIB ID: 024309692
• Web Site: http://id.ndl.go.jp/bib/024309692
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I024309692
• Web Site: http://www.jstage.jst.go.jp/article/ipsjtcva/1/0/1_0_277/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed