Snapshot coherent diffraction imaging via a physics-embedded untrained neural network
Optics Letters · 01.12.2024 · 49 (23) · 6701
DOI: 10.1364/ol.537909 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 21.11.2024. Verfasst von Yixiao Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 21 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Scholarship Council.
Abstract (Originalsprache)
Coherent diffraction imaging (CDI) is a lens-free imaging paradigm that avoids the diffraction limit caused by lens chromatic aberration. However, due to the ill-posed problem of phase retrieval, experiments often require the collection of multiple diffraction patterns for image reconstruction, which limits its application in dynamic imaging scenarios. In this Letter, we propose a physics-embedded untrained neural network for snapshot coherent diffraction imaging. Our network embeds a physical model of diffraction propagation and can be trained in an unsupervised learning paradigm. Moreover, the proposed method is applicable to complex-valued samples and is flexible for various imaging settings. Simulation and experiments demonstrate that the proposed physics-embedded network architecture performs better and achieves state-of-the-art results in snapshot CDI, compared with existing unsupervised methods.
Förderung
- National Natural Science Foundation of China
- China Scholarship Council
Zitieren
APA
Yang, Y., Li, Z., Yang, X., Liu, Z., & Tao, R. (2024). Snapshot coherent diffraction imaging via a physics-embedded untrained neural network. Optics Letters, 49(23), 6701. https://doi.org/10.1364/ol.537909
Vancouver
Yang Y, Li Z, Yang X, Liu Z, Tao R. Snapshot coherent diffraction imaging via a physics-embedded untrained neural network. Optics Letters. 2024;49(23):6701. doi:10.1364/ol.537909
BibTeX
@article{Yang2024,
author = {Yang, Yixiao and Li, Ziyang and Yang, Xiaodong and Liu, Zhengjun and Tao, Ran},
title = {Snapshot coherent diffraction imaging via a physics-embedded untrained neural network},
journal = {Optics Letters},
year = {2024},
volume = {49},
number = {23},
pages = {6701},
doi = {10.1364/ol.537909}
}
EUVIMED