Virtual view specification and synthesis in free viewpoint television application

Wenfeng Li, Jin Zhou, Baoxin Li, M. Ibrahim Sezan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In conventional TV, users can get only a single view of a real 3D world. The view is determined not by a user but by the camera position during acquisition. Free viewpoint television (FTV) is a new concept which aims at giving viewers the flexibility to select a novel viewpoint by employing multiple video streams as the input. Current proposed solutions for FTV include those based on ray-space sampling and interpolation. Most existing work makes the assumption that the cameras are calibrated. Moreover, virtual view specification is done in ways that would not be practical for actual use (e.g., some methods specify the virtual view by a rotation matrix and a translation vector). This paper proposes a framework for FTV based on image-based rendering, complete with key algorithms for color-based segmentation and correspondence, and multiple-image-based virtual view synthesis from uncalibrated cameras. Moreover, we propose an intuitive approach to specifying the virtual viewpoint, based on any two views chosen by the user. This makes the specification of the virtual view very intuitive and thus practical for the FTV application. Experiments with real video streams were performed to validate the proposed approaches.

Original languageEnglish (US)
Title of host publicationProceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Pages464-471
Number of pages8
DOIs
StatePublished - 2007
Event3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 - Chapel Hill, NC, United States
Duration: Jun 14 2006Jun 16 2006

Other

Other3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
CountryUnited States
CityChapel Hill, NC
Period6/14/066/16/06

Fingerprint

Television applications
Television
Cameras
Specifications
Interpolation
Sampling
Color
Experiments

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications

Cite this

Li, W., Zhou, J., Li, B., & Sezan, M. I. (2007). Virtual view specification and synthesis in free viewpoint television application. In Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 (pp. 464-471). [4155762] https://doi.org/10.1109/3DPVT.2006.145

Virtual view specification and synthesis in free viewpoint television application. / Li, Wenfeng; Zhou, Jin; Li, Baoxin; Sezan, M. Ibrahim.

Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. 2007. p. 464-471 4155762.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, W, Zhou, J, Li, B & Sezan, MI 2007, Virtual view specification and synthesis in free viewpoint television application. in Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006., 4155762, pp. 464-471, 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006, Chapel Hill, NC, United States, 6/14/06. https://doi.org/10.1109/3DPVT.2006.145
Li W, Zhou J, Li B, Sezan MI. Virtual view specification and synthesis in free viewpoint television application. In Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. 2007. p. 464-471. 4155762 https://doi.org/10.1109/3DPVT.2006.145
Li, Wenfeng ; Zhou, Jin ; Li, Baoxin ; Sezan, M. Ibrahim. / Virtual view specification and synthesis in free viewpoint television application. Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. 2007. pp. 464-471
@inproceedings{159b7de023d34856a90db42b5f50cd9f,
title = "Virtual view specification and synthesis in free viewpoint television application",
abstract = "In conventional TV, users can get only a single view of a real 3D world. The view is determined not by a user but by the camera position during acquisition. Free viewpoint television (FTV) is a new concept which aims at giving viewers the flexibility to select a novel viewpoint by employing multiple video streams as the input. Current proposed solutions for FTV include those based on ray-space sampling and interpolation. Most existing work makes the assumption that the cameras are calibrated. Moreover, virtual view specification is done in ways that would not be practical for actual use (e.g., some methods specify the virtual view by a rotation matrix and a translation vector). This paper proposes a framework for FTV based on image-based rendering, complete with key algorithms for color-based segmentation and correspondence, and multiple-image-based virtual view synthesis from uncalibrated cameras. Moreover, we propose an intuitive approach to specifying the virtual viewpoint, based on any two views chosen by the user. This makes the specification of the virtual view very intuitive and thus practical for the FTV application. Experiments with real video streams were performed to validate the proposed approaches.",
author = "Wenfeng Li and Jin Zhou and Baoxin Li and Sezan, {M. Ibrahim}",
year = "2007",
doi = "10.1109/3DPVT.2006.145",
language = "English (US)",
isbn = "0769528252",
pages = "464--471",
booktitle = "Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006",

}

TY - GEN

T1 - Virtual view specification and synthesis in free viewpoint television application

AU - Li, Wenfeng

AU - Zhou, Jin

AU - Li, Baoxin

AU - Sezan, M. Ibrahim

PY - 2007

Y1 - 2007

N2 - In conventional TV, users can get only a single view of a real 3D world. The view is determined not by a user but by the camera position during acquisition. Free viewpoint television (FTV) is a new concept which aims at giving viewers the flexibility to select a novel viewpoint by employing multiple video streams as the input. Current proposed solutions for FTV include those based on ray-space sampling and interpolation. Most existing work makes the assumption that the cameras are calibrated. Moreover, virtual view specification is done in ways that would not be practical for actual use (e.g., some methods specify the virtual view by a rotation matrix and a translation vector). This paper proposes a framework for FTV based on image-based rendering, complete with key algorithms for color-based segmentation and correspondence, and multiple-image-based virtual view synthesis from uncalibrated cameras. Moreover, we propose an intuitive approach to specifying the virtual viewpoint, based on any two views chosen by the user. This makes the specification of the virtual view very intuitive and thus practical for the FTV application. Experiments with real video streams were performed to validate the proposed approaches.

AB - In conventional TV, users can get only a single view of a real 3D world. The view is determined not by a user but by the camera position during acquisition. Free viewpoint television (FTV) is a new concept which aims at giving viewers the flexibility to select a novel viewpoint by employing multiple video streams as the input. Current proposed solutions for FTV include those based on ray-space sampling and interpolation. Most existing work makes the assumption that the cameras are calibrated. Moreover, virtual view specification is done in ways that would not be practical for actual use (e.g., some methods specify the virtual view by a rotation matrix and a translation vector). This paper proposes a framework for FTV based on image-based rendering, complete with key algorithms for color-based segmentation and correspondence, and multiple-image-based virtual view synthesis from uncalibrated cameras. Moreover, we propose an intuitive approach to specifying the virtual viewpoint, based on any two views chosen by the user. This makes the specification of the virtual view very intuitive and thus practical for the FTV application. Experiments with real video streams were performed to validate the proposed approaches.

UR - http://www.scopus.com/inward/record.url?scp=47249133376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47249133376&partnerID=8YFLogxK

U2 - 10.1109/3DPVT.2006.145

DO - 10.1109/3DPVT.2006.145

M3 - Conference contribution

SN - 0769528252

SN - 9780769528250

SP - 464

EP - 471

BT - Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

ER -