Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction

2023/06/19 by Oliver Hoidn, Hoidn, Oliver, Aashwin Mishra +3 · 9 citations
Physics and Astronomy · #Adaptive optics and wavefront sensing #Advanced X-ray Imaging Techniques #Astrophysical Phenomena and Observations #Computational Physics (physics.comp-ph) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Physical sciences #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Optics (physics.optics) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2306.11014

openalex publication_date 2023/06/19 · openalex created_date 2023/06/22 · openalex updated_date 2026/07/28

Abstract

By circumventing the resolution limitations of optics, coherent diffractive imaging (CDI) and ptychography are making their way into scientific fields ranging from X-ray imaging to astronomy. Yet, the need for time consuming iterative phase recovery hampers real-time imaging. While supervised deep learning strategies have increased reconstruction speed, they sacrifice image quality. Furthermore, these methods' demand for extensive labeled training data is experimentally burdensome. Here, we propose an unsupervised physics-informed neural network reconstruction method, PtychoPINN, that retains the factor of 100-to-1000 speedup of deep learning-based reconstruction while improving reconstruction quality by combining the diffraction forward map with real-space constraints from overlapping measurements. In particular, PtychoPINN significantly advances generalizability, accuracy (with a typical 10 dB PSNR increase), and linear resolution (2- to 6-fold gain). This blend of performance and speed offers exciting prospects for high-resolution real-time imaging in high-throughput environments such as X-ray free electron lasers (XFELs) and diffraction-limited light sources.

Cited by

• Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models
• Towards generalizable deep ptychography neural networks
• Learning neural representations for X-ray ptychography reconstruction with unknown probes
• Towards Physics Constrained Deep Learning Based Turbulence Model Uncertainty Quantification
• Fidelity-preserving enhancement of ptychography with foundational text-to-image models
• Improving Multislice Electron Ptychography with a Generative Prior
• DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis
• A Start To End Machine Learning Approach To Maximize Scientific Throughput From The LCLS-II-HE
• Contrast-invariant deep ptychography neural networks

Related

• Deep Learning Coherent Diffractive Imaging
• Constraint-Free Coherent Diffraction Imaging via Physics-Guided Neural Fields
• Real-time sparse-sampled Ptychographic imaging through deep neural networks
• A Physics-Inspired Deep Learning Framework with Polar Coordinate Attention for Ptychographic Imaging
• AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging