WEKO3
アイテム
Motion History Volume for Spatiotemporal Editing of 3D Video in Multi-party Interaction Scenes
https://ipsj.ixsq.nii.ac.jp/records/92513
https://ipsj.ixsq.nii.ac.jp/records/9251322109904-7a17-4c0e-b7a2-b5e2689431a7
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-CVIM13187048.pdf (4.5 MB)
|
Copyright (c) 2013 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | SIG Technical Reports(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2013-05-23 | |||||||
| タイトル | ||||||||
| タイトル | Motion History Volume for Spatiotemporal Editing of 3D Video in Multi-party Interaction Scenes | |||||||
| タイトル | ||||||||
| 言語 | en | |||||||
| タイトル | Motion History Volume for Spatiotemporal Editing of 3D Video in Multi-party Interaction Scenes | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | コメント制度セッション | |||||||
| 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 | ||||||||
| Kyoto University | ||||||||
| 著者所属 | ||||||||
| Kyoto University | ||||||||
| 著者所属 | ||||||||
| Kyoto University | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| Kyoto University | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| Kyoto University | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| Kyoto University | ||||||||
| 著者名 |
Qun, Shi
× Qun, Shi
|
|||||||
| 著者名(英) |
Qun, Shi
× Qun, Shi
|
|||||||
| 論文抄録 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | In this paper we present a novel method that performs spatiotemporal editing of 3D multi-party interaction scenes for free-viewpoint browsing, from separately captured data. The main idea is to first propose the augmented Motion History Volume (MHV) for motion representation. Then by modeling the correlations between different MHVs we can define a multi-party interaction dictionary, describing the spatiotemporal constraints for different types of multi-party interaction events. Finally, constraint satisfaction and global optimization methods are proposed to synthesize natural and continuous multi-party interaction scenes. Experiments with real data illustrate the effectiveness of our method. | |||||||
| 論文抄録(英) | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | In this paper we present a novel method that performs spatiotemporal editing of 3D multi-party interaction scenes for free-viewpoint browsing, from separately captured data. The main idea is to first propose the augmented Motion History Volume (MHV) for motion representation. Then by modeling the correlations between different MHVs we can define a multi-party interaction dictionary, describing the spatiotemporal constraints for different types of multi-party interaction events. Finally, constraint satisfaction and global optimization methods are proposed to synthesize natural and continuous multi-party interaction scenes. Experiments with real data illustrate the effectiveness of our method. | |||||||
| 書誌レコードID | ||||||||
| 収録物識別子タイプ | NCID | |||||||
| 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 2013-CVIM-187, 号 48, p. 1-7, 発行日 2013-05-23 |
|||||||
| 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 | |||||||
