Virtual view specification and synthesis for free viewpoint television

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

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Free viewpoint television (FTV) is a new concept that 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 rayspace resampling which demand at least dozens of cameras and large storage and transmission resources for those video streams. Image-based rendering (IBR) methods that rely on dense depth map estimation also face practical difficulties since accurate depth map estimation remains a challenging problem. This paper proposes a framework for FTV based on IBR that relieves the need for an accurate depth map by introducing a hybrid virtual view synthesis method. The framework also includes an intuitive method for virtual view specification in uncalibrated views. We present both simulation and real data experiments to validate the proposed framework and the component algorithms.

Original languageEnglish (US)
Article number4797842
Pages (from-to)533-546
Number of pages14
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume19
Issue number4
DOIs
StatePublished - Apr 2009

Fingerprint

Television
Specifications
Cameras
Experiments

Keywords

  • 3-D TV
  • Image-based rendering
  • View specification
  • View synthesis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

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

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 19, No. 4, 4797842, 04.2009, p. 533-546.

Research output: Contribution to journalArticle

@article{7ff5ea97e8824d7aade34ca9a1912104,
title = "Virtual view specification and synthesis for free viewpoint television",
abstract = "Free viewpoint television (FTV) is a new concept that 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 rayspace resampling which demand at least dozens of cameras and large storage and transmission resources for those video streams. Image-based rendering (IBR) methods that rely on dense depth map estimation also face practical difficulties since accurate depth map estimation remains a challenging problem. This paper proposes a framework for FTV based on IBR that relieves the need for an accurate depth map by introducing a hybrid virtual view synthesis method. The framework also includes an intuitive method for virtual view specification in uncalibrated views. We present both simulation and real data experiments to validate the proposed framework and the component algorithms.",
keywords = "3-D TV, Image-based rendering, View specification, View synthesis",
author = "Wenfeng Li and Jin Zhou and Baoxin Li and {Ibrahim Sezan}, M.",
year = "2009",
month = "4",
doi = "10.1109/TCSVT.2009.2014021",
language = "English (US)",
volume = "19",
pages = "533--546",
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 - Virtual view specification and synthesis for free viewpoint television

AU - Li, Wenfeng

AU - Zhou, Jin

AU - Li, Baoxin

AU - Ibrahim Sezan, M.

PY - 2009/4

Y1 - 2009/4

N2 - Free viewpoint television (FTV) is a new concept that 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 rayspace resampling which demand at least dozens of cameras and large storage and transmission resources for those video streams. Image-based rendering (IBR) methods that rely on dense depth map estimation also face practical difficulties since accurate depth map estimation remains a challenging problem. This paper proposes a framework for FTV based on IBR that relieves the need for an accurate depth map by introducing a hybrid virtual view synthesis method. The framework also includes an intuitive method for virtual view specification in uncalibrated views. We present both simulation and real data experiments to validate the proposed framework and the component algorithms.

AB - Free viewpoint television (FTV) is a new concept that 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 rayspace resampling which demand at least dozens of cameras and large storage and transmission resources for those video streams. Image-based rendering (IBR) methods that rely on dense depth map estimation also face practical difficulties since accurate depth map estimation remains a challenging problem. This paper proposes a framework for FTV based on IBR that relieves the need for an accurate depth map by introducing a hybrid virtual view synthesis method. The framework also includes an intuitive method for virtual view specification in uncalibrated views. We present both simulation and real data experiments to validate the proposed framework and the component algorithms.

KW - 3-D TV

KW - Image-based rendering

KW - View specification

KW - View synthesis

UR - http://www.scopus.com/inward/record.url?scp=66349095180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66349095180&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2009.2014021

DO - 10.1109/TCSVT.2009.2014021

M3 - Article

AN - SCOPUS:66349095180

VL - 19

SP - 533

EP - 546

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 4

M1 - 4797842

ER -