EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps

Emanuele Caruso iD, Francesco Pelosin iD, Alessandro Simoni iD, Oswald Lanz iD

Journal of Imaging · 16.03.2026 · 12 (3) · 132

DOI: 10.3390/jimaging12030132 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 16.03.2026. Verfasst von Emanuele Caruso und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering, Free University of Bozen-Bolzano, 39100 Bozen-Bolzano, Italy. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Covision Lab Scarl, Schaeffler Automotive Buehl GmbH, Open Access Publishing Fund of the Free University of Bozen-Bolzano.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Synthetic dataset generation in Computer Vision, particularly for industrial applications, is still underexplored. Industrial defect segmentation, for instance, requires highly accurate labels, yet acquiring such data is costly and time-consuming. To address this challenge, we propose a novel diffusion-based pipeline for generating high-fidelity industrial datasets with minimal supervision. Our approach conditions the diffusion model on enriched bounding-box representations to produce precise segmentation masks, ensuring realistic and accurately localized defect synthesis. Compared to existing layout-conditioned generative methods, our approach improves defect consistency and spatial accuracy. We introduce two quantitative metrics to evaluate the effectiveness of our method and assess its impact on a downstream segmentation task trained on real and synthetic data. Our results demonstrate that diffusion-based synthesis can bridge the gap between artificial and real-world industrial data, fostering more reliable and cost-efficient segmentation models.

Schlagwörter

Stichwörter der Autor:innen

bounding-box conditioningdefect segmentationdiffusion modelsindustrial inspectionsynthetic data

Autor:innen und Institutionen

  • Department of Engineering, Free University of Bozen-Bolzano, 39100 Bozen-Bolzano, Italy.
  • Covision Lab Scarl, 39042 Brixen-Bressanone, Italy.

ORCID-Profile: Emanuele Caruso, Francesco Pelosin, Alessandro Simoni, Oswald Lanz

Förderung

  • Covision Lab Scarl
  • Schaeffler Automotive Buehl GmbH
  • Open Access Publishing Fund of the Free University of Bozen-Bolzano

Zitieren

APA

Caruso, E., Pelosin, F., Simoni, A., & Lanz, O. (2026). Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps. Journal of Imaging, 12(3), 132. https://doi.org/10.3390/jimaging12030132

Vancouver

Caruso E, Pelosin F, Simoni A, Lanz O. Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps. Journal of Imaging. 2026;12(3):132. doi:10.3390/jimaging12030132

BibTeX
@article{Caruso2026,
  author = {Caruso, Emanuele and Pelosin, Francesco and Simoni, Alessandro and Lanz, Oswald},
  title = {Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Maps},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {3},
  pages = {132},
  doi = {10.3390/jimaging12030132}
}
Kostenlos starten →