AbSynth: Using Abstract Image Synthesis for Synthetic Training

Penk D, Horn M, Strohmeyer C, Egger B, Stamminger M, Bauer F (2024)

Publication Type: Conference contribution

Publication year: 2024

Publisher: Science and Technology Publications, Lda

Book Volume: 2

Pages Range: 718-729

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

Event location: Rome, ITA

DOI: 10.5220/0012431400003660

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 provide 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.

Authors with CRIS profile

Involved external institutions

Schaeffler Technologies AG & Co. KG Germany (DE)

How to cite

APA:

Penk, D., Horn, M., Strohmeyer, C., Egger, B., Stamminger, M., & Bauer, F. (2024). AbSynth: Using Abstract Image Synthesis for Synthetic Training. In Petia Radeva, Antonino Furnari, Kadi Bouatouch, A. Augusto Sousa (Eds.), Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (pp. 718-729). Rome, ITA: Science and Technology Publications, Lda.

MLA:

Penk, Dominik, et al. "AbSynth: Using Abstract Image Synthesis for Synthetic Training." Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2024, Rome, ITA Ed. Petia Radeva, Antonino Furnari, Kadi Bouatouch, A. Augusto Sousa, Science and Technology Publications, Lda, 2024. 718-729.

BibTeX: Download