Model-based synthetic view generation from a monocular video sequence

Chun-Jen Tsai; Peter Eisert; Bernd Girod; Aggelos K. Katsaggelos

doi:10.1109/ICIP.1997.647802

Model-based synthetic view generation from a monocular video sequence

Chun-Jen Tsai^*, Peter Eisert, Bernd Girod, Aggelos K. Katsaggelos

^*此作品的通信作者

資訊工程學系

研究成果 › 同行評審

6 引文斯高帕斯（Scopus）

摘要

In this paper a model-based multi-view image generation system for video conferencing is presented. The system assumes that a 3-D model of the person in front of the camera is available. It extracts texture from a speaking person sequence images and maps it to the static 3-D model during the video conference session. Since only the incrementally updated texture information is transmitted during the whole session, the bandwidth requirement is very small. Based on the experimental results one can conclude that the proposed system is very promising for practical applications.

原文	English
頁面	444-447
頁數	4
DOIs	https://doi.org/10.1109/ICIP.1997.647802
出版狀態	Published - 1997
事件	Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) - Santa Barbara, CA, USA 持續時間: 26 10月 1997 → 29 10月 1997

Conference

Conference	Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3)
城市	Santa Barbara, CA, USA
期間	26/10/97 → 29/10/97

存取文件

10.1109/ICIP.1997.647802

其它文件與鏈接

Link to publication in Scopus

引用此

@conference{31026fb566fb4d9fb816a86769cf4670,

title = "Model-based synthetic view generation from a monocular video sequence",

abstract = "In this paper a model-based multi-view image generation system for video conferencing is presented. The system assumes that a 3-D model of the person in front of the camera is available. It extracts texture from a speaking person sequence images and maps it to the static 3-D model during the video conference session. Since only the incrementally updated texture information is transmitted during the whole session, the bandwidth requirement is very small. Based on the experimental results one can conclude that the proposed system is very promising for practical applications.",

author = "Chun-Jen Tsai and Peter Eisert and Bernd Girod and Katsaggelos, {Aggelos K.}",

year = "1997",

doi = "10.1109/ICIP.1997.647802",

language = "English",

pages = "444--447",

note = "Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) ; Conference date: 26-10-1997 Through 29-10-1997",

}

TY - CONF

T1 - Model-based synthetic view generation from a monocular video sequence

AU - Tsai, Chun-Jen

AU - Eisert, Peter

AU - Girod, Bernd

AU - Katsaggelos, Aggelos K.

PY - 1997

Y1 - 1997

N2 - In this paper a model-based multi-view image generation system for video conferencing is presented. The system assumes that a 3-D model of the person in front of the camera is available. It extracts texture from a speaking person sequence images and maps it to the static 3-D model during the video conference session. Since only the incrementally updated texture information is transmitted during the whole session, the bandwidth requirement is very small. Based on the experimental results one can conclude that the proposed system is very promising for practical applications.

AB - In this paper a model-based multi-view image generation system for video conferencing is presented. The system assumes that a 3-D model of the person in front of the camera is available. It extracts texture from a speaking person sequence images and maps it to the static 3-D model during the video conference session. Since only the incrementally updated texture information is transmitted during the whole session, the bandwidth requirement is very small. Based on the experimental results one can conclude that the proposed system is very promising for practical applications.

UR - http://www.scopus.com/inward/record.url?scp=0031380451&partnerID=8YFLogxK

U2 - 10.1109/ICIP.1997.647802

DO - 10.1109/ICIP.1997.647802

M3 - Paper

AN - SCOPUS:0031380451

SP - 444

EP - 447

T2 - Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3)

Y2 - 26 October 1997 through 29 October 1997

ER -

Model-based synthetic view generation from a monocular video sequence

摘要

Conference

存取文件

其它文件與鏈接

指紋

引用此