DeepSCI: scalable speckle correlation imaging using physics-enhanced deep learning
Optics Letters · 01.05.2023 · 48 (9) · 2285
DOI: 10.1364/ol.484867 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 20.04.2023. Verfasst von Zhiwei Tang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 21 Literaturangaben. Gefördert von: Program of Shanghai Academic Research Leader, National Natural Science Foundation of China, Chinesisch-Deutsche Zentrum für Wissenschaftsförderung.
Abstract (Originalsprache)
In this Letter we present a physics-enhanced deep learning approach for speckle correlation imaging (SCI), i.e., DeepSCI. DeepSCI incorporates the theoretical model of SCI into both the training and test stages of a neural network to achieve interpretable data preprocessing and model-driven fine-tuning, allowing the full use of data and physics priors. It can accurately reconstruct the image from the speckle pattern and is highly scalable to both medium perturbations and domain shifts. Our experimental results demonstrate the suitability and effectiveness of DeepSCI for solving the problem of limited generalization generally encountered in data-driven approaches.
Förderung
- Program of Shanghai Academic Research Leader
- National Natural Science Foundation of China
- Chinesisch-Deutsche Zentrum für Wissenschaftsförderung
Zitieren
APA
Tang, Z., Wang, F., Fu, Z., Zheng, S., Jin, Y., & Situ, G. (2023). DeepSCI: scalable speckle correlation imaging using physics-enhanced deep learning. Optics Letters, 48(9), 2285. https://doi.org/10.1364/ol.484867
Vancouver
Tang Z, Wang F, Fu Z, Zheng S, Jin Y, Situ G. DeepSCI: scalable speckle correlation imaging using physics-enhanced deep learning. Optics Letters. 2023;48(9):2285. doi:10.1364/ol.484867
BibTeX
@article{Tang2023,
author = {Tang, Zhiwei and Wang, Fei and Fu, ZhenFeng and Zheng, Shanshan and Jin, Ying and Situ, Guohai},
title = {DeepSCI: scalable speckle correlation imaging using physics-enhanced deep learning},
journal = {Optics Letters},
year = {2023},
volume = {48},
number = {9},
pages = {2285},
doi = {10.1364/ol.484867}
}
EUVIMED