Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Teaching 3D Geometry to Deformable Part Models

Pepik, B., Stark, M., Gehler, P., & Schiele, B. (2012). Teaching 3D Geometry to Deformable Part Models. In 2012 IEEE Conference on Computer Vision and Pattern Recognition (pp. 3362-3369). Piscataway, NJ: IEEE. doi:10.1109/CVPR.2012.6248075.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag
Latex : Teaching {3D} Geometry to Deformable Part Models

Dateien

einblenden: Dateien
ausblenden: Dateien
:
pepik12cvpr.pdf (Preprint), 9MB
 
Datei-Permalink:
-
Name:
pepik12cvpr.pdf
Beschreibung:
-
OA-Status:
Sichtbarkeit:
Privat
MIME-Typ / Prüfsumme:
application/pdf
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-
Lizenz:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Pepik, Bojan1, Autor           
Stark, Michael1, Autor           
Gehler, Peter2, Autor           
Schiele, Bernt1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497642              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Cognition , Design automation , Detectors , Estimation , Optimization , Solid modeling , Training geometry , image representation , object recognition , object tracking , teaching 2D bounding box localization , 3D geometric reasoning , 3D geometry teaching , 3D object tracking , 3D scene understanding , Pascal VOC , benchmark data set , deformable part model , higher-level application , individual object detection , object class detector output , object class recognition system , object hypothesis , representational gap , scene understanding system , ultra-wide baseline matching , viewpoint estimation
 Zusammenfassung: Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the detection of individual objects, higher-level applications such as 3D scene understanding or 3D object tracking would benefit from more fine-grained object hypotheses incorporating 3D geometric information, such as viewpoints or the locations of individual parts. In this paper, we help narrowing the representational gap between the ideal input of a scene understanding system and object class detector output, by designing a detector particularly tailored towards 3D geometric reasoning. In particular, we extend the successful discriminatively trained deformable part models to include both estimates of viewpoint and 3D parts that are consistent across viewpoints. We experimentally verify that adding 3D geometric information comes at minimal performance loss w.r.t. 2D bounding box localization, but outperforms prior work in 3D viewpoint estimation and ultra-wide baseline matching.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20122012
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1109/CVPR.2012.6248075
BibTex Citekey: pepik12cvpr
Anderer: Local-ID: 69C776F3F5006035C12579C10041F4B2-pepik12cvpr
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: IEEE Conference on Computer Vision and Pattern Recognition
Veranstaltungsort: Providence, RI
Start-/Enddatum: 2012-06-16 - 2012-06-21

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 2012 IEEE Conference on Computer Vision and Pattern Recognition
  Kurztitel : CVPR 2012
Genre der Quelle: Konferenzband
 Urheber:
Belongie, Serge1, Autor
Blake, Andrew1, Autor
Luo, Jiebo1, Autor
Yuille, Alan1, Autor
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Piscataway, NJ : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 3362 - 3369 Identifikator: ISBN: 978-1-4673-1226-4
ISSN: 1063-6919