Low-Photon Holographic Phase Retrieval via a Deep Decoder Neural Network (JTu5A.19)
Presenter: David Barmherzig, Flatiron Institute
A deep decoder neural network is applied towards the enhancement of recent algorithms for holographic Coherent Diffraction Imaging (CDI). This method does not require training data, and provides improved imaging given noisy low-photon CDI data.
Authors:Hannah Lawrence, Massachusetts Institute of Technology / David Barmherzig, Flatiron Institute / Michael Eickenberg, Flatiron Institute / Marylou Gabrie, New York University