| Item type |
SIG Technical Reports(1) |
| 公開日 |
2022-09-29 |
| タイトル |
|
|
タイトル |
パフォーマンス撮影のための演者立ち位置情報を基にしたカメラ位置姿勢生成手法 |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Camera Position and Pose Generation Method Based on Performer's Standing Position for Performance Shooting |
| 言語 |
|
|
言語 |
jpn |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
計測・認証2 |
| 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 |
|
|
|
筑波大学システム情報工学研究群 |
| 著者所属 |
|
|
|
筑波大学計算科学研究センター |
| 著者所属 |
|
|
|
筑波大学計算科学研究センター |
| 著者所属(英) |
|
|
|
en |
|
|
Degree programs in Systems and Information Engineering, University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
Center for Computational Sciences, University of Tsukuba |
| 著者所属(英) |
|
|
|
en |
|
|
Center for Computational Sciences, University of Tsukuba |
| 著者名 |
逸見, 勲
宍戸, 英彦
北原, 格
|
| 著者名(英) |
Isao, Hemmi
Hidehiko, Shishido
Itaru, Kitahara
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
The quality of the video is greatly affected by the camerawork. Unlike filming a movie, it is hard to reshoot live entertainment. Therefore, it is more important to consider the camerawork based on the information obtained in advance. The methods to generate camerawork using scenarios have been proposed, however, the methods have not considered changes in the standing positions of the performers on the stage yet. This study proposes an automatic camera work generation method that uses deep learning to output camera positions and postures for each scene based on the standing positions of the performers in each scene (keyframe) obtained from the stage script. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
The quality of the video is greatly affected by the camerawork. Unlike filming a movie, it is hard to reshoot live entertainment. Therefore, it is more important to consider the camerawork based on the information obtained in advance. The methods to generate camerawork using scenarios have been proposed, however, the methods have not considered changes in the standing positions of the performers on the stage yet. This study proposes an automatic camera work generation method that uses deep learning to output camera positions and postures for each scene based on the standing positions of the performers in each scene (keyframe) obtained from the stage script. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA12049625 |
| 書誌情報 |
研究報告エンタテインメントコンピューティング（EC）
巻 2022-EC-65,
号 37,
p. 1-5,
発行日 2022-09-29
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8914 |
| 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 |
IPSJ-EC22065037.pdf (1.5 MB)
