Authors:
Dominik Penk
1
;
2
;
Maik Horn
2
;
Christoph Strohmeyer
2
;
Bernhard Egger
1
;
Marc Stamminger
1
and
Frank Bauer
1
Affiliations:
1
Chair of Visual Computing, Friedrich-Alexander-Universität Erlangen-Nürnberg, Cauerstraße 11, Erlangen, Germany
;
2
Schaeffler Technologies AG & Co. KG, Industriestraße 1-3, Herzogenaurach, Germany
Keyword(s):
Synthetic Training Data, Domain Gap, Deep Learning, Computer Vision.
Abstract:
We present a novel pipeline for training neural networks to tackle geometry-induced vision tasks, relying solely on synthetic training images generated from (geometric) CAD models of the objects under consideration. Instead of aiming for photorealistic renderings, our approach maps both synthetic and real-world data onto a common abstract image space reducing the domain gap. We demonstrate that this projection can be decoupled from the downstream task, making our method an easy drop-in solution for a variety of applications. In this paper, we use line images as our chosen abstract image representation due to their ability to capture geometric properties effectively. We introduce an efficient training data synthesis method, that generates images tailored for transformation into a line representation. Additionally, we explore how the use of sparse line images opens up new possibilities for augmenting the dataset, enhancing the overall robustness of the downstream models. Finally, we pr
ovide an evaluation of our pipeline and augmentation techniques across a range of vision tasks and state-of-the-art models, showcasing their effectiveness and potential for practical applications.
(More)