3D Pose Estimation from Color Images without Manual Annotations

Mahdi Rad, Markus Oberweger, Vincent Lepetit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Buch/BerichtBegutachtung

Abstract

3D pose estimation is an important problem with many potential applications. However, 3D acquiring annotations for color images is a difficult task. To create training data, the annotating is usually done with the help of markers or a robotic system, which in both cases is very cumbersome, expensive, or sometimes even impossible, especially from color images. Another option is to use synthetic images for training. However, synthetic images do not resemble real images exactly. To bridge this domain gap, Generative Adversarial Networks or transfer learning techniques can be used but, they require some annotated real images to learn the domain transfer. To overcome these problems, we propose a novel approach in this paper. Section II gives a short summary of our approach that uses synthetic data only, and Section III shows some results.
Originalspracheenglisch
TitelProceedings of the joint OAGM & ARW Workshop 2019
Redakteure/-innenAndreas Pichler, Peter M. Roth, Robert Slabatnig, Gernot Stübl
ErscheinungsortGraz
Herausgeber (Verlag)Verlag der Technischen Universität Graz
Seitenumfang1
ISBN (elektronisch)9783851256635
DOIs
PublikationsstatusVeröffentlicht - 2019
Veranstaltung43rd Annual Workshop of the Austrian Association for Pattern Recognition: Vision and Robotics: ÖAGM 2019 - Steyr, Österreich
Dauer: 9 Mai 201910 Mai 2019

Konferenz

Konferenz43rd Annual Workshop of the Austrian Association for Pattern Recognition: Vision and Robotics
Land/GebietÖsterreich
OrtSteyr
Zeitraum9/05/1910/05/19

Fingerprint

Untersuchen Sie die Forschungsthemen von „3D Pose Estimation from Color Images without Manual Annotations“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren