Efficiently synthesizing virtual video

Richard J. Radke; Peter J. Ramadge; Sanjeev R. Kulkarni; Tomio Echigo

doi:10.1109/TCSVT.2003.811364

Efficiently synthesizing virtual video

Richard J. Radke, Peter J. Ramadge, Sanjeev R. Kulkarni, Tomio Echigo

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Given a set of synchronized video sequence of a dynamic scene taken by different cameras, we address the problem of creating a virtual video of the scene from a novel viewpoint. A key aspect of our algorithm is a method for recursively propagating dense and physically accurate correspondences between the two video sources. By exploiting temporal continuity and suitably constraining the correspondences, we provide an efficient framework for synthesizing realistic virtual video. The stability of the propagation algorithm is analyzed, and experimental results are presented.

Original language	English (US)
Pages (from-to)	325-337
Number of pages	13
Journal	IEEE Transactions on Circuits and Systems for Video Technology
Volume	13
Issue number	4
DOIs	https://doi.org/10.1109/TCSVT.2003.811364
State	Published - Apr 2003

All Science Journal Classification (ASJC) codes

Media Technology
Electrical and Electronic Engineering

Keywords

Correspondence
Image-based rendering
View synthesis
Virtual video
Virtual views

Access to Document

10.1109/TCSVT.2003.811364

Cite this

@article{4ac44455e3814253888c032dd519ef0d,

title = "Efficiently synthesizing virtual video",

abstract = "Given a set of synchronized video sequence of a dynamic scene taken by different cameras, we address the problem of creating a virtual video of the scene from a novel viewpoint. A key aspect of our algorithm is a method for recursively propagating dense and physically accurate correspondences between the two video sources. By exploiting temporal continuity and suitably constraining the correspondences, we provide an efficient framework for synthesizing realistic virtual video. The stability of the propagation algorithm is analyzed, and experimental results are presented.",

keywords = "Correspondence, Image-based rendering, View synthesis, Virtual video, Virtual views",

author = "Radke, {Richard J.} and Ramadge, {Peter J.} and Kulkarni, {Sanjeev R.} and Tomio Echigo",

note = "Funding Information: Manuscript received January 16, 2002; revised January 10, 2003. This research was supported in part by grants from the IBM Tokyo Research Laboratory, the New Jersey Center for Multimedia Research, the U.S. Army Research Office under contract number DAAD19-00-1-0466, and NSF KDI under contract number ECS-9873451.",

year = "2003",

month = apr,

doi = "10.1109/TCSVT.2003.811364",

language = "English (US)",

volume = "13",

pages = "325--337",

journal = "IEEE Transactions on Circuits and Systems for Video Technology",

issn = "1051-8215",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Efficiently synthesizing virtual video

AU - Radke, Richard J.

AU - Ramadge, Peter J.

AU - Kulkarni, Sanjeev R.

AU - Echigo, Tomio

N1 - Funding Information: Manuscript received January 16, 2002; revised January 10, 2003. This research was supported in part by grants from the IBM Tokyo Research Laboratory, the New Jersey Center for Multimedia Research, the U.S. Army Research Office under contract number DAAD19-00-1-0466, and NSF KDI under contract number ECS-9873451.

PY - 2003/4

Y1 - 2003/4

N2 - Given a set of synchronized video sequence of a dynamic scene taken by different cameras, we address the problem of creating a virtual video of the scene from a novel viewpoint. A key aspect of our algorithm is a method for recursively propagating dense and physically accurate correspondences between the two video sources. By exploiting temporal continuity and suitably constraining the correspondences, we provide an efficient framework for synthesizing realistic virtual video. The stability of the propagation algorithm is analyzed, and experimental results are presented.

AB - Given a set of synchronized video sequence of a dynamic scene taken by different cameras, we address the problem of creating a virtual video of the scene from a novel viewpoint. A key aspect of our algorithm is a method for recursively propagating dense and physically accurate correspondences between the two video sources. By exploiting temporal continuity and suitably constraining the correspondences, we provide an efficient framework for synthesizing realistic virtual video. The stability of the propagation algorithm is analyzed, and experimental results are presented.

KW - Correspondence

KW - Image-based rendering

KW - View synthesis

KW - Virtual video

KW - Virtual views

UR - http://www.scopus.com/inward/record.url?scp=0038623149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038623149&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2003.811364

DO - 10.1109/TCSVT.2003.811364

M3 - Article

AN - SCOPUS:0038623149

SN - 1051-8215

VL - 13

SP - 325

EP - 337

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

IS - 4

ER -

Efficiently synthesizing virtual video

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this