4-K-resolution minimalist optical system design based on deep learning
Applied Optics · 01.02.2024 · 63 (4) · 917
DOI: 10.1364/ao.510860 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, online erschienen am 22.01.2024. Verfasst von Dexiao Meng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In order to simplify optical systems, we propose a high-resolution minimalist optical design method based on deep learning. Unlike most imaging system design work, we combine optical design more closely with image processing algorithms. For optical design, we separately study the impact of different aberrations on computational imaging and then innovatively propose an aberration metric and a spatially micro-variant design method that better meet the needs of image recognition. For image processing, we construct a dataset based on the point spread function (PSF) imaging simulation method. In addition, we use a non-blind deblurring computational imaging method to repair spatially variant aberrations. Finally, we achieve clear imaging at 4 K (5184×3888) using only two spherical lenses and achieve image quality similar to that of complex lenses on the market.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Meng, D., Zhou, Y., & Bai, J. (2024). 4-K-resolution minimalist optical system design based on deep learning. Applied Optics, 63(4), 917. https://doi.org/10.1364/ao.510860
Vancouver
Meng D, Zhou Y, Bai J. 4-K-resolution minimalist optical system design based on deep learning. Applied Optics. 2024;63(4):917. doi:10.1364/ao.510860
BibTeX
@article{Meng2024,
author = {Meng, Dexiao and Zhou, Yan and Bai, Jian},
title = {4-K-resolution minimalist optical system design based on deep learning},
journal = {Applied Optics},
year = {2024},
volume = {63},
number = {4},
pages = {917},
doi = {10.1364/ao.510860}
}
EUVIMED