DeNos22: A Pipeline to Learn Object Tracking Using Simulated Depth

Penk D, Horn M, Strohmeyer C, Bauer F, Stamminger M (2023)


Publication Type: Conference contribution

Publication year: 2023

Original Authors: Dominik Penk, Maik Horn, Christoph Strohmeyer, Frank Bauer, Marc Stamminger

Series: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Conference Proceedings Title: Volume 5: VISAPP,

Event location: Lisbon PT

DOI: 10.5220/0011635100003417

Abstract

Abstract: We propose a novel pipeline to construct a learning based 6D object pose tracker, which is solely trained on synthetic depth images. The only required input is a (geometric) CAD model of the target object. Training data is synthesized by rendering stereo images of the CAD model, in front of a large variety of backgrounds generated by point-based re-renderings of prerecorded background scenes. Finally, depth from stereo is applied in order to mimic the behavior of depth sensors. The synthesized training input generalizes well to real-world scenes, but we further show how to improve real-world inference using robust estimators to counteract the errors introduced by the sim-to-real transfer. As a result, we show that our 6D pose trackers achieve state-of-the-art results without any annotated real-world data, solely based on a CAD-model of the target object.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Penk, D., Horn, M., Strohmeyer, C., Bauer, F., & Stamminger, M. (2023). DeNos22: A Pipeline to Learn Object Tracking Using Simulated Depth. In Volume 5: VISAPP,. Lisbon, PT.

MLA:

Penk, Dominik, et al. "DeNos22: A Pipeline to Learn Object Tracking Using Simulated Depth." Proceedings of the Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,, Lisbon 2023.

BibTeX: Download