Autor:	Guohai Situ, Ruibo Shang, Geoffrey P. Luke, Fei Wang, Kevin Hoffer-Hawlik
Rok vydání:	2021
Předmět:	Artificial neural network business.industry Deep learning Two step Prior probability Structured illumination microscopy Computer vision Image processing Artificial intelligence Iterative reconstruction business Image (mathematics)
Zdroj:	OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP).
DOI:	10.1364/cosi.2021.cm6b.5
Popis:	A two-step deep learning approach is proposed for computational imaging. This approach is robust to image model mismatches since physics priors are not needed and mitigates over-parameterization by training the network in 2 steps.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d70ade4f077c1359ef841c3da62aad86 https://doi.org/10.1364/cosi.2021.cm6b.5 Zobrazit plný text záznamu