Real-time coherent diffraction inversion using deep generative networks

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, precluding real-time imaging. 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.

References in corpus (8)

• Image reconstruction by domain transform manifold learning
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• X-ray image reconstruction from a diffraction pattern alone
• High-resolution ab initio three-dimensional X-ray diffraction microscopy
• Sparsity-based single-shot sub-wavelength coherent diffractive imaging
• Deep learning enhanced mobile-phone microscopy
• prDeep: Robust Phase Retrieval with a Flexible Deep Network
• A Learning Approach to Optical Tomography

Cited by in corpus (21)

• On the use of deep learning for phase recovery
• A Data Ecosystem to Support Machine Learning in Materials Science
• PhaseGAN: A deep-learning phase-retrieval approach for unpaired datasets
• Three-dimensional Coherent X-ray Diffraction Imaging via Deep Convolutional Neural Networks
• Multi-scale Convolutional Neural Networks for Inverse Problems
• Real-time 3D Nanoscale Coherent Imaging via Physics-aware Deep Learning
• Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging
• Time-resolved x-ray microscopy for materials science
• Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders
• Deep learning phase recovery: data-driven, physics-driven, or combining both?
• Deep Hybrid Scattering Image Learning
• Artifact Identification in X-ray Diffraction Data using Machine Learning Methods
• Reconstruction of nanoscale particles from single-shot wide-angle FEL diffractions patterns with physics-informed neural networks
• Real-time phase-retrieval and wavefront sensing enabled by an artificial neural network
• Machine learning enabled surrogate crystal plasticity model for spatially resolved 3D orientation evolution under uniaxial tension
• Neural Network Methods for Radiation Detectors and Imaging
• Noise-robust latent vector reconstruction in ptychography using deep generative models
• Deep-learning real-time phase retrieval of imperfect diffraction patterns from X-ray free-electron lasers
• Investigating the robustness of a learning-based method for quantitative phase retrieval from propagation-based x-ray phase contrast measurements under laboratory conditions
• Fast reconstruction of single-shot wide-angle diffraction images through deep learning
• The Future of the Correlated Electron Problem