Sundermeyer, Martin und Marton, Zoltan-Csaba und Durner, Maximilian und Brucker, Manuel und Triebel, Rudolph (2018) Implicit 3D Orientation Learning for 6D Object Detection from RGB Images. In: 15th European Conference on Computer Vision, ECCV 2018, 11210, Seiten 712-729. Springer, Cham. European Conference on Computer Vision, 2018-09-10 - 2018-09-13, Munich, Germany. doi: 10.1007/978-3-030-01231-1_43. ISBN 978-3-030-01230-4. ISSN 0302-9743.
![]() |
PDF
10MB |
Offizielle URL: https://link.springer.com/chapter/10.1007/978-3-030-01231-1_43
Kurzfassung
We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization. This so-called Augmented Autoencoder has several advantages over existing methods: It does not require real, pose-annotated training data, generalizes to various test sensors and inherently handles object and view symmetries. Instead of learning an explicit mapping from input images to object poses, it provides an implicit representation of object orientations defined by samples in a latent space. Experiments on the T-LESS and LineMOD datasets show that our method outperforms similar model-based approaches and competes with state-of-the art approaches that require real pose-annotated images.
elib-URL des Eintrags: | https://elib.dlr.de/122011/ | ||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Poster, Programmrede) | ||||||||||||||||||||||||
Titel: | Implicit 3D Orientation Learning for 6D Object Detection from RGB Images | ||||||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||||||
Datum: | 10 September 2018 | ||||||||||||||||||||||||
Erschienen in: | 15th European Conference on Computer Vision, ECCV 2018 | ||||||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||||||||||
Band: | 11210 | ||||||||||||||||||||||||
DOI: | 10.1007/978-3-030-01231-1_43 | ||||||||||||||||||||||||
Seitenbereich: | Seiten 712-729 | ||||||||||||||||||||||||
Verlag: | Springer, Cham | ||||||||||||||||||||||||
Name der Reihe: | Lecture Notes in Computer Science | ||||||||||||||||||||||||
ISSN: | 0302-9743 | ||||||||||||||||||||||||
ISBN: | 978-3-030-01230-4 | ||||||||||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||||||||||
Stichwörter: | 6D Object Detection, Pose Estimation, Domain Randomization, Autoencoder, Synthetic Data, Pose Ambiguity, Symmetries | ||||||||||||||||||||||||
Veranstaltungstitel: | European Conference on Computer Vision | ||||||||||||||||||||||||
Veranstaltungsort: | Munich, Germany | ||||||||||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||||||||||
Veranstaltungsbeginn: | 10 September 2018 | ||||||||||||||||||||||||
Veranstaltungsende: | 13 September 2018 | ||||||||||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||||||||||||||
HGF - Programmthema: | Technik für Raumfahrtsysteme | ||||||||||||||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||||||||||
DLR - Forschungsgebiet: | R SY - Technik für Raumfahrtsysteme | ||||||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Vorhaben Multisensorielle Weltmodellierung (alt) | ||||||||||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) > Perzeption und Kognition | ||||||||||||||||||||||||
Hinterlegt von: | Sundermeyer, Martin | ||||||||||||||||||||||||
Hinterlegt am: | 30 Nov 2018 00:39 | ||||||||||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:26 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags