Higher-order clique reduction in binary graph cut

Hiroshi Ishikawa*

*この研究の対応する著者

研究成果: Conference contribution

96 被引用数 (Scopus)

抄録

We introduce a new technique that can reduce any higher-order Markov random field with binary labels into a first-order one that has the same minima as the original. Moreover, we combine the reduction with the fusion-move and QPBO algorithms to optimize higher-order multi-label problems. While many vision problems today are formulated as energy minimization problems, they have mostly been limited to using first-order energies, which consist of unary and pairwise clique potentials, with a few exceptions that consider triples. This is because of the lack of efficient algorithms to optimize energies with higher-order interactions. Our algorithm challenges this restriction that limits the representational power of the models, so that higherorder energies can be used to capture the rich statistics of natural scenes. To demonstrate the algorithm, we minimize a third-order energy, which allows clique potentials with up to four pixels, in an image restoration problem. The problem uses the Fields of Experts model, a learned spatial prior of natural images that has been used to test two belief propagation algorithms capable of optimizing higher-order energies. The results show that the algorithm exceeds the BP algorithms in both optimization performance and speed.

本文言語English
ホスト出版物のタイトル2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
出版社IEEE Computer Society
ページ2993-3000
ページ数8
ISBN(印刷版)9781424439935
DOI
出版ステータスPublished - 2009 1 1
外部発表はい
イベント2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Miami, FL, United States
継続期間: 2009 6 202009 6 25

出版物シリーズ

名前2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
2009 IEEE Computer Society Conference on Computer Vision and ...

Conference

Conference2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
国/地域United States
CityMiami, FL
Period09/6/2009/6/25

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識
  • 生体医工学

フィンガープリント

「Higher-order clique reduction in binary graph cut」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