Spatial frequency learning improves atomic resolution electron microscope images
Spatial-Frequency Learning for Scanning Transmission Electron Microscopy Image Enhancement
Computer Vision and Pattern Recognition
Summary
Images from powerful electron microscopes can be hard to understand because they are blurry and noisy. The authors developed a new computer method that improves these images by looking at patterns in two ways: by their position and by their repeating structures. They also created a way to make more realistic fake images to train their method better. This method helps show tiny details of materials more clearly in microscope images and makes finding atoms more accurate.
What this means in practice
- •For materials characterization teams: Enhance microscope images to better identify atomic structures and interfaces in advanced materials under noisy conditions.
- •For semiconductor manufacturing engineers: Improve clarity of electron microscopy images for more accurate defect detection and quality control in chip fabrication.
Authors
Hesong Li, Ying Fu, Ziqi Wu, Ruiwen Shao, Tao Zhang
Abstract
Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution and plays a key role in the discovery and characterization of advanced materials. Raw STEM images are often noisy and blurred due to multiple degradations. Although recent deep learning methods improve STEM images, their performance remains limited under severe degradations. In this work, we propose a spatial-frequency learning framework for STEM image enhancement. Specifically, we design a spatial-frequency fusion network that exploits periodic atomic arrangements in the frequency domain and restores local atomic details in the spatial domain. Spatial- and frequency-domain features are enhanced separately and then fused. We also present a STEM noise calibration method for synthesizing more realistic STEM images. The parameters of scan noise, pointwise noise, and background noise are estimated through statistical analysis and fitting of real STEM images. Using these calibrated parameters, we construct a diverse dataset containing a wider range of atomic arrangements, imaging modes, and degradations. Random masks combine different atomic arrangements to simulate interfaces between multiple materials. Experimental results demonstrate that our method achieves state-of-the-art enhancement performance on synthetic datasets and real images of advanced materials while improving atomic localization accuracy.