Freeform optical system design with differentiable three-dimensional ray tracing and unsupervised learning
Optics Express · 27.02.2023 · 31 (5) · 7450
DOI: 10.1364/oe.484531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 14.02.2023. Verfasst von Yunfeng Nie und 3 weiteren Autor:innen. Die Arbeit wurde bisher 62-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: H2020 Future and Emerging Technologies, Vrije Universiteit Brussel, Fonds Wetenschappelijk Onderzoek.
Abstract (Originalsprache)
Optical systems have been crucial for versatile applications such as consumer electronics, remote sensing and biomedical imaging. Designing optical systems has been a highly professional work due to complicated aberration theories and intangible rules-of-thumb, hence neural networks are only coming into this realm until recent years. In this work, we propose and implement a generic, differentiable freeform raytracing module, suitable for off-axis, multiple-surface freeform/aspheric optical systems, paving the way toward a deep learning-based optical design method. The network is trained with minimal prior knowledge, and it can infer numerous optical systems after a one-time training. The presented work unlocks great potential for deep learning in various freeform/aspheric optical systems, and the trained network could serve as an effective, unified platform for generating, recording, and replicating good initial optical designs.
Förderung
- H2020 Future and Emerging Technologies
- Vrije Universiteit Brussel
- Fonds Wetenschappelijk Onderzoek
Zitieren
APA
Nie, Y., Zhang, J., Su, R., & Ottevaere, H. (2023). Freeform optical system design with differentiable three-dimensional ray tracing and unsupervised learning. Optics Express, 31(5), 7450. https://doi.org/10.1364/oe.484531
Vancouver
Nie Y, Zhang J, Su R, Ottevaere H. Freeform optical system design with differentiable three-dimensional ray tracing and unsupervised learning. Optics Express. 2023;31(5):7450. doi:10.1364/oe.484531
BibTeX
@article{Nie2023,
author = {Nie, Yunfeng and Zhang, Jingang and Su, Runmu and Ottevaere, Heidi},
title = {Freeform optical system design with differentiable three-dimensional ray tracing and unsupervised learning},
journal = {Optics Express},
year = {2023},
volume = {31},
number = {5},
pages = {7450},
doi = {10.1364/oe.484531}
}
EUVIMED