Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

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

: Rojtberg, Pavel; Pöllabauer, Thomas Jürgen; Kuijper, Arjan


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
IEEE International Conference on Artificial Intelligence and Virtual Reality, AIVR 2020. Proceedings : Virtual Conference, 14-18 December 2020
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-7464-8
ISBN: 978-1-7281-7463-1
International Conference on Artificial Intelligence and Virtual Reality (AIVR) <3, 2020, Online>
Fraunhofer IGD ()
training; Solid Modeling; pose estimation; data models; Lead Topic: Visual Computing as a Service; Research Line: Computer graphics (CG); Research Line: Computer vision (CV)

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.