Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging
arXiv:2008.10094 · doi:10.1063/5.0014725
Abstract
We present a novel adaptive machine-learning based approach for reconstructing three-dimensional (3D) crystals from coherent diffraction imaging (CDI). We represent the crystals using spherical harmonics (SH) and generate corresponding synthetic diffraction patterns. We utilize 3D convolutional neural networks (CNN) to learn a mapping between 3D diffraction volumes and the SH which describe the boundary of the physical volumes from which they were generated. We use the 3D CNN-predicted SH coefficients as the initial guesses which are then fine tuned using adaptive model independent feedback for improved accuracy.
References in corpus (13)
- Phase recovery and holographic image reconstruction using deep learning in neural networks
- A unified evaluation of iterative projection algorithms for phase retrieval
- Relaxed Averaged Alternating Reflections for Diffraction Imaging
- Low Photon Count Phase Retrieval Using Deep Learning
- Quantitative Imaging of Single, Unstained Viruses with Coherent X-rays
- Real-time coherent diffraction inversion using deep generative networks
- Using Automatic Differentiation as a General Framework for Ptychographic Reconstruction
- Accelerating lattice quantum Monte Carlo simulation using artificial neural networks: an application to the Holstein model
- Exact representations of many body interactions with RBM neural networks
- Phase retrieval for Bragg coherent diffraction imaging at high X-ray energies
- prDeep: Robust Phase Retrieval with a Flexible Deep Network
- High-energy coherent X-ray diffraction microscopy of polycrystal grains: first steps towards a multi-scale approach
- Machine learning enabled surrogate crystal plasticity model for spatially resolved 3D orientation evolution under uniaxial tension