Real-Time Atomic-Resolution Electron Phase Imaging without Probe Calibration via Ptychography-Supervised Learning
Abstract
Atomic-scale phase imaging is central to resolving defects, interfaces, and weakly scattering atoms that govern the behavior of nanoscale materials. Electron ptychography delivers sub-ångström phase sensitivity but remains an offline technique, because its iterative reconstruction is computationally expensive and sensitive to experimental calibration, preventing live use during data acquisition. Here, a ptychography-supervised local inference framework is presented that converts four-dimensional scanning transmission electron microscopy (4D-STEM) into an acquisition-compatible phase-imaging workflow. Physics-constrained reference phase maps reconstructed from a single experimental AuPd dataset serve as teacher labels for a compact model that predicts local phase patches directly from diffraction measurements, without explicit probe input or online iterative optimization. Full-field images are assembled by deterministic overlap stitching. The workflow reaches an online latency of about 0.27 ms per probe position and a throughput of about 20,000 positions per second, an approximately 1,000-fold speed-up over GPU-accelerated ePIE, while preserving atomic-scale lattice contrast and reciprocal-space fidelity. Without fine-tuning, the same model transfers across materials (WS2), defocus conditions (high-entropy alloy nanoparticles), and instruments (hBN at 300 kV). The approach amortizes ptychographic redundancy into a fast, generalizable workflow that enables real-time atomic-scale phase imaging for materials microscopy.
Related
- A unified self-supervised framework for single-frame Fresnel CDI and overlapped ptychography
- Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters
- Learning Transferable Self-Supervised Priors for Super-Resolution Reconstruction in Structured Illumination Microscopy
- Trade-off between interface morphology and compositional homogeneity in AlGaAs/GaAs quantum wells revealed by multislice electron ptychography
- Assessing quantitative phase reliability in electron ptychography using a twisted trilayer WS2 thickness staircase
BibTeX
@misc{yue2026realtime,
title = {{Real-Time Atomic-Resolution Electron Phase Imaging without Probe Calibration via Ptychography-Supervised Learning}},
author = {H. Yue and C. -C. Chen and C. -N. Hsiao and J. Cheng and Y. Liu and X. Z. Liao and Steve F. Shu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25684},
eprint = {2609.25684},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25684},
}
RIS
TY - UNPB
TI - Real-Time Atomic-Resolution Electron Phase Imaging without Probe Calibration via Ptychography-Supervised Learning
AU - H. Yue
AU - C. -C. Chen
AU - C. -N. Hsiao
AU - J. Cheng
AU - Y. Liu
AU - X. Z. Liao
AU - Steve F. Shu
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.25684
UR - https://arxiv.org/abs/2609.25684
AB - Atomic-scale phase imaging is central to resolving defects, interfaces, and weakly scattering atoms that govern the behavior of nanoscale materials. Electron ptychography delivers sub-ångström phase sensitivity but remains an offline technique, because its iterative reconstruction is computationally expensive and sensitive to experimental calibration, preventing live use during data acquisition. Here, a ptychography-supervised local inference framework is presented that converts four-dimensional scanning transmission electron microscopy (4D-STEM) into an acquisition-compatible phase-imaging workflow. Physics-constrained reference phase maps reconstructed from a single experimental AuPd dataset serve as teacher labels for a compact model that predicts local phase patches directly from diffraction measurements, without explicit probe input or online iterative optimization. Full-field images are assembled by deterministic overlap stitching. The workflow reaches an online latency of about 0.27 ms per probe position and a throughput of about 20,000 positions per second, an approximately 1,000-fold speed-up over GPU-accelerated ePIE, while preserving atomic-scale lattice contrast and reciprocal-space fidelity. Without fine-tuning, the same model transfers across materials (WS2), defocus conditions (high-entropy alloy nanoparticles), and instruments (hBN at 300 kV). The approach amortizes ptychographic redundancy into a fast, generalizable workflow that enables real-time atomic-scale phase imaging for materials microscopy.
ER -