An Efficient Octree Design for Local Variational Range Image Fusion

Marniok, Nico; Johannsen, Ole; Goldlücke, Bastian

An Efficient Octree Design for Local Variational Range Image Fusion

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2017

Autor:innen

Marniok, Nico

Johannsen, Ole

Goldlücke, Bastian

DOI (zitierfähiger Link)

https://doi.org/10.1007/978-3-319-66709-6_32

EU-Projektnummer

336978

Projekt

LIA - Light Field Imaging and Analysis

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

ROTH, Volker, ed., Thomas VETTER, ed.. Pattern Recognition. Cham: Springer, 2017, pp. 401-412. Lecture Notes in Computer Science. 10496. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-66708-9. Available under: doi: 10.1007/978-3-319-66709-6_32

Zusammenfassung

We present a reconstruction pipeline for a large-scale 3D environment viewed by a single moving RGB-D camera. Our approach combines advantages of fast and direct, regularization-free depth fusion and accurate, but costly variational schemes. The scene’s depth geometry is extracted from each camera view and efficiently integrated into a large, dense grid as a truncated signed distance function, which is organized in an octree. To account for noisy real-world input data, variational range image integration is performed in local regions of the volume directly on this octree structure. We focus on algorithms which are easily parallelizable on GPUs, allowing the pipeline to be used in real-time scenarios where the user can interactively view the reconstruction and adapt camera motion as required.

Fachgebiet (DDC)

004 Informatik

Konferenz

39th German Conference : GCPR 2017 Proceedings, 12. Sep. 2017 - 15. Sep. 2017, Basel, Switzerland

Zitieren

ISO 690

MARNIOK, Nico, Ole JOHANNSEN, Bastian GOLDLÜCKE, 2017. An Efficient Octree Design for Local Variational Range Image Fusion. 39th German Conference : GCPR 2017 Proceedings. Basel, Switzerland, 12. Sep. 2017 - 15. Sep. 2017. In: ROTH, Volker, ed., Thomas VETTER, ed.. Pattern Recognition. Cham: Springer, 2017, pp. 401-412. Lecture Notes in Computer Science. 10496. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-66708-9. Available under: doi: 10.1007/978-3-319-66709-6_32

BibTex

@inproceedings{Marniok2017Effic-42780,
  year={2017},
  doi={10.1007/978-3-319-66709-6_32},
  title={An Efficient Octree Design for Local Variational Range Image Fusion},
  number={10496},
  isbn={978-3-319-66708-9},
  issn={0302-9743},
  publisher={Springer},
  address={Cham},
  series={Lecture Notes in Computer Science},
  booktitle={Pattern Recognition},
  pages={401--412},
  editor={Roth, Volker and Vetter, Thomas},
  author={Marniok, Nico and Johannsen, Ole and Goldlücke, Bastian}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/42780">
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-07-04T16:38:02Z</dcterms:available>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Marniok, Nico</dc:contributor>
    <dc:creator>Marniok, Nico</dc:creator>
    <dc:creator>Johannsen, Ole</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Johannsen, Ole</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/42780"/>
    <dcterms:title>An Efficient Octree Design for Local Variational Range Image Fusion</dcterms:title>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-07-04T16:38:02Z</dc:date>
    <dc:language>eng</dc:language>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:abstract xml:lang="eng">We present a reconstruction pipeline for a large-scale 3D environment viewed by a single moving RGB-D camera. Our approach combines advantages of fast and direct, regularization-free depth fusion and accurate, but costly variational schemes. The scene’s depth geometry is extracted from each camera view and efficiently integrated into a large, dense grid as a truncated signed distance function, which is organized in an octree. To account for noisy real-world input data, variational range image integration is performed in local regions of the volume directly on this octree structure. We focus on algorithms which are easily parallelizable on GPUs, allowing the pipeline to be used in real-time scenarios where the user can interactively view the reconstruction and adapt camera motion as required.</dcterms:abstract>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:issued>2017</dcterms:issued>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja