Contrastive Image-Metadata Pre-Training for Materials Transmission Electron Microscopy

2026-04-27

AI Summary

This work addresses the underutilization of vast archives of transmission electron microscopy (TEM) data and their associated instrument parameter metadata. The authors propose a novel unpaired, physics-aware style transfer method that, for the first time, aligns high-angle annular dark-field scanning TEM (HAADF-STEM) images with their automatically recorded acquisition metadata through contrastive learning. This approach constructs a joint embedding space between images and metadata and integrates a generative network to enable metadata-conditioned image style transfer and denoising. Evaluated on a dataset of 7,330 real HAADF-STEM images, the method effectively synthesizes image appearances corresponding to diverse instrument settings and significantly enhances image quality, establishing a new paradigm for reusing unpublished electron microscopy data.

Abstract

The vast majority of transmission electron microscopy (TEM) data never gets published and ends up on a backup drive until deleted to free up space. These left-over datasets are rich in detail and variation, often paired with automatically saved metadata of instrument state and acquisition parameters. In this work, we introduce a dataset of 7,330 high-angle annular dark-field scanning-TEM (HAADF-STEM) images from a single instrument to learn a joint embedding space between image metadata and HAADF image. These embeddings link image style with acquisition parameters, which allows us to train a generative style transfer network that can convert experimental images into the style they would have had if they were recorded with different instrument parameters. We evaluate the performance of the network and explore the usefulness of the technique for physical denoising.

Problem

• Transmission Electron Microscopy
• Image-Metadata Embedding
• HAADF-STEM
• Style Transfer
• Unpublished TEM Data

Innovation

• contrastive pre-training
• image-metadata embedding
• HAADF-STEM
• generative style transfer
• physical denoising