Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Joint 3D-reconstruction and Background Separation in Multiple Views using Graph Cuts

Goldluecke, B., & Magnor, M. (2003). Joint 3D-reconstruction and Background Separation in Multiple Views using Graph Cuts. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR-03) (pp. 683-694). Los Alamitos, USA: IEEE.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-2D5A-F Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-2D5B-D
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Goldluecke, Bastian1, 2, Autor           
Magnor, Marcus2, Autor           
Affiliations:
1International Max Planck Research School, MPI for Informatics, Max Planck Society, ou_1116551              
2Graphics - Optics - Vision, MPI for Informatics, Max Planck Society, ou_1116549              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: This paper deals with simultaneous depth map estimation and background separation in a multi-view setting with several fixed calibrated cameras, two problems which have previously been addressed separately. We demonstrate that their strong interdependency can be exploited elegantly by minimizing a discrete energy functional which evaluates both properties at the same time. Our algorithm is derived from the powerful ``Multi-Camera Scene Reconstruction via Graph Cuts'' algorithm recently presented by Kolmogorov and Zabih. Experiments with both real-world as well as synthetic scenes demonstrate that the presented combined approach yields even more correct depth estimates. In particular, the additional information gained by taking background into account increases considerably the algorithm's robustness against noise.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2004-07-072003
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: Los Alamitos, USA : IEEE
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eDoc: 202037
Anderer: Local-ID: C1256BDE005F57A8-52D68D202CC0ACD1C1256CF000485E8A-Goldluecke2003:joint
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Untitled Event
Veranstaltungsort: Madison, Wisconsin, USA
Start-/Enddatum: 2003-06-18

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR-03)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Los Alamitos, USA : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 683 - 694 Identifikator: ISBN: 0-7695-1900-8