Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  VConv-DAE: Deep Volumetric Shape Learning Without Object Labels

Sharma, A., Grau, O., & Fritz, M. (2016). VConv-DAE: Deep Volumetric Shape Learning Without Object Labels. In G. Hua, & H. Jégou (Eds.), Computer Vision - ECCV 2016 Workshops (pp. 236-250). Berlin: Springer. doi:10.1007/978-3-319-49409-8_20.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-002B-0642-6 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-002C-3C6A-8
Genre: Konferenzbeitrag
Latex : {VConv}-{DAE}: {D}eep Volumetric Shape Learning Without Object Labels

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Sharma, Abhishek1, Autor           
Grau, Oliver2, Autor
Fritz, Mario1, Autor           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Graphics, cs.GR
 Zusammenfassung: With the advent of affordable depth sensors, 3D capture becomes more and more ubiquitous and already has made its way into commercial products. Yet, capturing the geometry or complete shapes of everyday objects using scanning devices (eg. Kinect) still comes with several challenges that result in noise or even incomplete shapes. Recent success in deep learning has shown how to learn complex shape distributions in a data-driven way from large scale 3D CAD Model collections and to utilize them for 3D processing on volumetric representations and thereby circumventing problems of topology and tessellation. Prior work has shown encouraging results on problems ranging from shape completion to recognition. We provide an analysis of such approaches and discover that training as well as the resulting representation are strongly and unnecessarily tied to the notion of object labels. Furthermore, deep learning research argues ~\cite{Vincent08} that learning representation with over-complete model are more prone to overfitting compared to the approach that learns from noisy data. Thus, we investigate a full convolutional volumetric denoising auto encoder that is trained in a unsupervised fashion. It outperforms prior work on recognition as well as more challenging tasks like denoising and shape completion. In addition, our approach is atleast two order of magnitude faster at test time and thus, provides a path to scaling up 3D deep learning.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2016-04-132016-09-09201620162016
 Publikationsstatus: Erschienen
 Seiten: 16 p.
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: Sharma_arXiv2016
DOI: 10.1007/978-3-319-49409-8_20
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Geometry Meets Deep Learning ECCV 2016 Workshop
Veranstaltungsort: Amsterdam, The Netherlands
Start-/Enddatum: 2016-10-09 - 2016-10-09

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Computer Vision - ECCV 2016 Workshops
  Kurztitel : ECCV-W 2016
  Andere : ECCV 2016
  Andere : ECCV 2016 W6 Geometry Meets Deep Learning
  Untertitel : Amsterdam, The Netherlands, October 8 -10 and 15–16, 2016; Proceedings, Part III
Genre der Quelle: Konferenzband
 Urheber:
Hua, Gang1, Herausgeber
Jégou, Hervé1, Herausgeber
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Berlin : Springer
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 236 - 250 Identifikator: ISBN: 978-3-319-49408-1

Quelle 2

einblenden:
ausblenden:
Titel: Lecture Notes in Computer Science
  Kurztitel : LNCS
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 9915 Artikelnummer: - Start- / Endseite: - Identifikator: -