Fast and robust progressive stereo reconstruction by symmetry guided fusion

Hongsheng Zhang, Shahriar Negahdaripour

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

8 Citations (Scopus)

Abstract

Acquiring photo-realistic 3D computer models of objects has been a very active research area with most important applications in Virtual Reality and Multimedia systems. This paper deals with a generalization of dense stereo reconstruction, which forms the basis for incremental fusing of stereo sequences to construct a 3-D model of underwater natural objects. The approach is fast and robust. Initialized with a set of robust feature matches over the left and right images, efficient left-to-right and right-to-left stereo matching are carried out by match propagation [15]. Symmetry relation between the two stereo matchings is utilized to guide robust fusion. Where a large difference exists between the two dense stereo reconstructions, it is most probable that at least one estimate is erroneous, thus is rejected. Conversely, small differences are expected because of the discrete nature of the disparity values. When fused these two estimates, better results are expected. Experimental results demonstrate the efficacy of the proposed approach.

Original languageEnglish
Title of host publicationOceans 2005 - Europe
Pages551-556
Number of pages6
Volume1
DOIs
StatePublished - Dec 1 2005
EventOceans 2005 - Europe - Brest, France
Duration: Jun 20 2005Jun 23 2005

Other

OtherOceans 2005 - Europe
CountryFrance
CityBrest
Period6/20/056/23/05

Fingerprint

Fusion reactions
Multimedia systems
Virtual reality

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Fast and robust progressive stereo reconstruction by symmetry guided fusion. / Zhang, Hongsheng; Negahdaripour, Shahriar.

Oceans 2005 - Europe. Vol. 1 2005. p. 551-556 1511774.

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

Zhang, H & Negahdaripour, S 2005, Fast and robust progressive stereo reconstruction by symmetry guided fusion. in Oceans 2005 - Europe. vol. 1, 1511774, pp. 551-556, Oceans 2005 - Europe, Brest, France, 6/20/05. https://doi.org/10.1109/OCEANSE.2005.1511774
Zhang, Hongsheng ; Negahdaripour, Shahriar. / Fast and robust progressive stereo reconstruction by symmetry guided fusion. Oceans 2005 - Europe. Vol. 1 2005. pp. 551-556
@inproceedings{32ac171faf6b4ff9ae14f33af1f45935,
title = "Fast and robust progressive stereo reconstruction by symmetry guided fusion",
abstract = "Acquiring photo-realistic 3D computer models of objects has been a very active research area with most important applications in Virtual Reality and Multimedia systems. This paper deals with a generalization of dense stereo reconstruction, which forms the basis for incremental fusing of stereo sequences to construct a 3-D model of underwater natural objects. The approach is fast and robust. Initialized with a set of robust feature matches over the left and right images, efficient left-to-right and right-to-left stereo matching are carried out by match propagation [15]. Symmetry relation between the two stereo matchings is utilized to guide robust fusion. Where a large difference exists between the two dense stereo reconstructions, it is most probable that at least one estimate is erroneous, thus is rejected. Conversely, small differences are expected because of the discrete nature of the disparity values. When fused these two estimates, better results are expected. Experimental results demonstrate the efficacy of the proposed approach.",
author = "Hongsheng Zhang and Shahriar Negahdaripour",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/OCEANSE.2005.1511774",
language = "English",
isbn = "0780391039",
volume = "1",
pages = "551--556",
booktitle = "Oceans 2005 - Europe",

}

TY - GEN

T1 - Fast and robust progressive stereo reconstruction by symmetry guided fusion

AU - Zhang, Hongsheng

AU - Negahdaripour, Shahriar

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Acquiring photo-realistic 3D computer models of objects has been a very active research area with most important applications in Virtual Reality and Multimedia systems. This paper deals with a generalization of dense stereo reconstruction, which forms the basis for incremental fusing of stereo sequences to construct a 3-D model of underwater natural objects. The approach is fast and robust. Initialized with a set of robust feature matches over the left and right images, efficient left-to-right and right-to-left stereo matching are carried out by match propagation [15]. Symmetry relation between the two stereo matchings is utilized to guide robust fusion. Where a large difference exists between the two dense stereo reconstructions, it is most probable that at least one estimate is erroneous, thus is rejected. Conversely, small differences are expected because of the discrete nature of the disparity values. When fused these two estimates, better results are expected. Experimental results demonstrate the efficacy of the proposed approach.

AB - Acquiring photo-realistic 3D computer models of objects has been a very active research area with most important applications in Virtual Reality and Multimedia systems. This paper deals with a generalization of dense stereo reconstruction, which forms the basis for incremental fusing of stereo sequences to construct a 3-D model of underwater natural objects. The approach is fast and robust. Initialized with a set of robust feature matches over the left and right images, efficient left-to-right and right-to-left stereo matching are carried out by match propagation [15]. Symmetry relation between the two stereo matchings is utilized to guide robust fusion. Where a large difference exists between the two dense stereo reconstructions, it is most probable that at least one estimate is erroneous, thus is rejected. Conversely, small differences are expected because of the discrete nature of the disparity values. When fused these two estimates, better results are expected. Experimental results demonstrate the efficacy of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=33746768117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746768117&partnerID=8YFLogxK

U2 - 10.1109/OCEANSE.2005.1511774

DO - 10.1109/OCEANSE.2005.1511774

M3 - Conference contribution

SN - 0780391039

SN - 9780780391031

VL - 1

SP - 551

EP - 556

BT - Oceans 2005 - Europe

ER -