Discrete Inference Approaches to Image Segmentation and Dense Correspondence

• Item type: SIG Technical Reports(1)
• 公開日: 2017-05-03
• タイトル: Discrete Inference Approaches to Image Segmentation and Dense Correspondence
• タイトル / 言語: en
• タイトル: Discrete Inference Approaches to Image Segmentation and Dense Correspondence
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: MVA/CVIM D論セッション
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: The University of Tokyo／RIKEN AIP
• 著者所属: The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo / RIKEN AIP
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者名: Tatsunori, Taniai; Yoichi, Sato
• 著者名(英): Tatsunori, Taniai; Yoichi, Sato
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: We consider discrete inference approaches to image segmentation and dense correspondence. The two problems cover diverse tasks such as image segmentation, binarization, cosegmentation, motion segmentation, binocular stereo vision, optical flow and general dense correspondence, which are addressed sorely or jointly in this work as energy minimization problems on Markov random fields. Discrete inference approaches are employed to effectively optimize inherently discrete functions or highly non-convex continuous functions. The contributions of this work are two folds: proposal of novel joint frameworks of image segmentation and dense correspondence problems, and development of new inference techniques for sole or joint tasks. Specifically, we comprehensively address three challenges of discrete inference, that is, label space size, higher-order energy, and non-submodular energy, which are posed in various forms in four tasks involving image segmentation and dense correspondence problems.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: We consider discrete inference approaches to image segmentation and dense correspondence. The two problems cover diverse tasks such as image segmentation, binarization, cosegmentation, motion segmentation, binocular stereo vision, optical flow and general dense correspondence, which are addressed sorely or jointly in this work as energy minimization problems on Markov random fields. Discrete inference approaches are employed to effectively optimize inherently discrete functions or highly non-convex continuous functions. The contributions of this work are two folds: proposal of novel joint frameworks of image segmentation and dense correspondence problems, and development of new inference techniques for sole or joint tasks. Specifically, we comprehensively address three challenges of discrete inference, that is, label space size, higher-order energy, and non-submodular energy, which are posed in various forms in four tasks involving image segmentation and dense correspondence problems.
• 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: AA11131797
• 書誌情報: 研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2017-CVIM-207, 号 37, p. 1-16, 発行日 2017-05-03
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8701
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会