Real-time coherent diffraction inversion using deep generative networks

Authors:
Top Cited Papers
Open Access
Publisher website
Google Scholar
Abstract
Phase retrieval, or the process of recovering phase information in reciprocal space to reconstruct images from measured intensity alone, is the underlying basis to a variety of imaging applications including coherent diffraction imaging (CDI). Typical phase retrieval algorithms are iterative in nature, and hence, are time-consuming and computationally expensive, making real-time imaging a challenge. Furthermore, iterative phase retrieval algorithms struggle to converge to the correct solution especially in the presence of strong phase structures. In this work, we demonstrate the training and testing of CDI NN, a pair of deep deconvolutional networks trained to predict structure and phase in real space of a 2D object from its corresponding far-field diffraction intensities alone. Once trained, CDI NN can invert a diffraction pattern to an image within a few milliseconds of compute time on a standard desktop machine, opening the door to real-time imaging.
Funding Information
  • Basic Energy Sciences (DE-AC02-06CH11357)
  • Basic Energy Sciences (DE-AC02-06CH11357)
  • Argonne National Laboratory (2018-019-N0)
  • Argonne National Laboratory (2018-019-N0)

This publication has 35 references indexed in Scilit: