EUVIMEDEUVIMED entdecken
Crossref

Deep learning–based distance estimation in incoherent digital holography

Shion Arai, Teruyoshi Nobukawa, Yasunobu Akiyama, Tetsuhiko Muroi

Optics Express · 29.06.2026 · 34 (13) · 23421

DOI: 10.1364/oe.600091 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 16.06.2026. Verfasst von Shion Arai und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Incoherent digital holography (IDH) can generate holograms using spatially incoherent light; however, distance information cannot be directly extracted from holograms. Herein, we propose deep learning-based methods for fast distance estimation in IDH. To efficiently and accurately generate datasets, we construct an IDH simulator that reflects a real-world IDH setup. Moreover, we propose a preprocessing technique that compensates for the phase offset inherent in the IDH system and enhances hologram contrast to effectively extract features of holograms. We numerically and experimentally demonstrate the fundamental principles and effectiveness of the proposed methods. This technique facilitates fast and accurate acquisition of three-dimensional information in IDH.

Zitieren

APA

Arai, S., Nobukawa, T., Akiyama, Y., & Muroi, T. (2026). Deep learning–based distance estimation in incoherent digital holography. Optics Express, 34(13), 23421. https://doi.org/10.1364/oe.600091

Vancouver

Arai S, Nobukawa T, Akiyama Y, Muroi T. Deep learning–based distance estimation in incoherent digital holography. Optics Express. 2026;34(13):23421. doi:10.1364/oe.600091

BibTeX
@article{Arai2026,
  author = {Arai, Shion and Nobukawa, Teruyoshi and Akiyama, Yasunobu and Muroi, Tetsuhiko},
  title = {Deep learning–based distance estimation in incoherent digital holography},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {13},
  pages = {23421},
  doi = {10.1364/oe.600091}
}
Kostenlos starten →