Characterizing geometric variability of industrial 3D models to guide preparation of synthetic datasets for machine learning applications
Proceedings of the Design Society · 2026-08 · 6 · 2531-2540
DOI: 10.1017/pds.2026.10611 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Design Society, online erschienen am 02.07.2026. Verfasst von Lovro Sever und 3 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This paper presents a characterization approach for analysing geometric variability in industrial 3D model datasets to support the preparation of synthetic datasets for machine-learning applications. By implementing pairwise Hausdorff distances and manifold-based embedding techniques, the study identifies variability ranges required for generating representative synthetic data and demonstrates how targeted augmentation can effectively reproduce real data’s variability, ultimately leading to more reliable and robust NN model performance.
Zitieren
APA
Sever, L., Kosec, P., Škec, S., & Martinec, T. (2026). Characterizing geometric variability of industrial 3D models to guide preparation of synthetic datasets for machine learning applications. Proceedings of the Design Society, 6, 2531-2540. https://doi.org/10.1017/pds.2026.10611
Vancouver
Sever L, Kosec P, Škec S, Martinec T. Characterizing geometric variability of industrial 3D models to guide preparation of synthetic datasets for machine learning applications. Proceedings of the Design Society. 2026;6:2531-2540. doi:10.1017/pds.2026.10611
BibTeX
@article{Sever2026,
author = {Sever, Lovro and Kosec, Petar and Škec, Stanko and Martinec, Tomislav},
title = {Characterizing geometric variability of industrial 3D models to guide preparation of synthetic datasets for machine learning applications},
journal = {Proceedings of the Design Society},
year = {2026},
volume = {6},
pages = {2531--2540},
doi = {10.1017/pds.2026.10611}
}
EUVIMED