This HTML5 document contains 43 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n15http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n16http://purl.org/net/nknouf/ns/bibtex#
n4http://localhost/temp/predkladatel/
n17http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n7http://linked.opendata.cz/resource/domain/vavai/projekt/
n10http://linked.opendata.cz/ontology/domain/vavai/
n19https://schema.org/
n5http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F68407700%3A21230%2F06%3A00124930%21RIV14-AV0-21230___/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n18http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n14http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n21http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n11http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F68407700%3A21230%2F06%3A00124930%21RIV14-AV0-21230___
rdf:type
n10:Vysledek skos:Concept
dcterms:description
This paper presents a new technique for estimating a multi-view reconstruction given pair-wise Euclidean reconstructions up to rotations, translations and scales. The partial reconstructions are glued by the following three step procedure: (i) Camera rotations consistent with all reconstructions are estimated linearly. (ii) All the pair-wise reconstructions are modified according to the new rotations and refined by bundle adjustment while keeping the corresponding rotations same. (iii) The refined rotations are used to estimate camera translations and 3D points using Second Order Cone Programming by minimizing the L-infinity-norm. We introduce a new criterion for evaluating importance of an epipolar geometry in influence on the overall 3D geometry. The estimated importance is used to reweight data in the above algorithm to better handle unequiponderantly captured images. The performance of the proposed method is demonstrated on difficult wide base-line image sets. This paper presents a new technique for estimating a multi-view reconstruction given pair-wise Euclidean reconstructions up to rotations, translations and scales. The partial reconstructions are glued by the following three step procedure: (i) Camera rotations consistent with all reconstructions are estimated linearly. (ii) All the pair-wise reconstructions are modified according to the new rotations and refined by bundle adjustment while keeping the corresponding rotations same. (iii) The refined rotations are used to estimate camera translations and 3D points using Second Order Cone Programming by minimizing the L-infinity-norm. We introduce a new criterion for evaluating importance of an epipolar geometry in influence on the overall 3D geometry. The estimated importance is used to reweight data in the above algorithm to better handle unequiponderantly captured images. The performance of the proposed method is demonstrated on difficult wide base-line image sets.
dcterms:title
3D Reconstruction by Gluing Pair-wise Euclidean Reconstructions, or ``How to Achieve a Good Reconstruction from Bad Images'' 3D Reconstruction by Gluing Pair-wise Euclidean Reconstructions, or ``How to Achieve a Good Reconstruction from Bad Images''
skos:prefLabel
3D Reconstruction by Gluing Pair-wise Euclidean Reconstructions, or ``How to Achieve a Good Reconstruction from Bad Images'' 3D Reconstruction by Gluing Pair-wise Euclidean Reconstructions, or ``How to Achieve a Good Reconstruction from Bad Images''
skos:notation
RIV/68407700:21230/06:00124930!RIV14-AV0-21230___
n3:aktivita
n8:P
n3:aktivity
P(1ET101210406)
n3:dodaniDat
n11:2014
n3:domaciTvurceVysledku
n17:6245269 n17:8641315
n3:druhVysledku
n20:D
n3:duvernostUdaju
n14:S
n3:entitaPredkladatele
n5:predkladatel
n3:idSjednocenehoVysledku
510655
n3:idVysledku
RIV/68407700:21230/06:00124930
n3:jazykVysledku
n21:eng
n3:klicovaSlova
factorization; metric reconstruction; missing data; structure from motion; wide base-line stereo
n3:klicoveSlovo
n18:structure%20from%20motion n18:metric%20reconstruction n18:wide%20base-line%20stereo n18:missing%20data n18:factorization
n3:kontrolniKodProRIV
[396EF5AB5597]
n3:mistoKonaniAkce
Chapel Hill, NC
n3:mistoVydani
Piscataway
n3:nazevZdroje
Third International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT)
n3:obor
n6:JD
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n7:1ET101210406
n3:rokUplatneniVysledku
n11:2006
n3:tvurceVysledku
Martinec, Daniel Pajdla, Tomáš
n3:typAkce
n15:WRD
n3:zahajeniAkce
2006-06-14+02:00
s:numberOfPages
8
n16:hasPublisher
IEEE
n19:isbn
978-0-7695-2825-0
n4:organizacniJednotka
21230