• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Style-transfer GANs for Bridging the Domain Gap in Synthetic Pose Estimator Training
 
  • Details
  • Full
Options
2020
  • Konferenzbeitrag

Titel

Style-transfer GANs for Bridging the Domain Gap in Synthetic Pose Estimator Training

Abstract
Given the dependency of current CNN architectures on a large training set, the possibility of using synthetic data is alluring as it allows generating a virtually infinite amount of labeled training data. However, producing such data is a nontrivial task as current CNN architectures are sensitive to the domain gap between real and synthetic data. We propose to adopt general-purpose GAN models for pixellevel image translation, allowing to formulate the domain gap itself as a learning problem. The obtained models are then used either during training or inference to bridge the domain gap. Here, we focus on training the single-stage YOLO6D [20] object pose estimator on synthetic CAD geometry only, where not even approximate surface information is available. When employing paired GAN models, we use an edge-based intermediate domain and introduce different mappings to represent the unknown surface properties. Our evaluation shows a considerable improvement in model performance when compared to a model trained with the same degree of domain randomization, while requiring only very little additional effort.
Author(s)
Rojtberg, Pavel
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Pöllabauer, Thomas Jürgen
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Kuijper, Arjan
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Hauptwerk
IEEE International Conference on Artificial Intelligence and Virtual Reality, AIVR 2020. Proceedings
Konferenz
International Conference on Artificial Intelligence and Virtual Reality (AIVR) 2020
Thumbnail Image
DOI
10.1109/AIVR50618.2020.00039
Language
Englisch
google-scholar
IGD
Tags
  • training

  • Solid Modeling

  • pose estimation

  • data models

  • Lead Topic: Visual Co...

  • Research Line: Comput...

  • Research Line: Comput...

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022