Abstract
We develop and explore a deep learning based single-shot ptychography reconstruction method. We show that a deep neural network, trained using only experimental data and without any model of the system, leads to reconstructions of natural real-valued images with higher spatial resolution and better resistance to systematic noise than common iterative algorithms.
Original language | English |
---|---|
Pages (from-to) | 17511-17520 |
Number of pages | 10 |
Journal | Optics Express |
Volume | 28 |
Issue number | 12 |
DOIs | |
State | Published - 8 Jun 2020 |
Externally published | Yes |