Scanning Electron Microscopy (SEM) is indispensable in modern materials science, enabling high-resolution imaging across a wide range of structural, chemical, and functional investigations. However, SEM imaging remains constrained by task-specific models and labor-intensive acquisition processes that limit its scalability across diverse applications. Here, we introduce the first foundation model for SEM images, pretrained on a large corpus of multi-instrument, multi-condition scientific micrographs, enabling generalization across diverse material systems and imaging conditions. Leveraging a self-supervised transformer architecture, our model learns rich and transferable representations that can be fine-tuned or adapted to a wide range of downstream tasks. As a compelling demonstration, we focus on defocus-to-focus image translation-an essential yet underexplored challenge in automated microscopy pipelines. Our method not only restores focused detail from defocused inputs without paired supervision but also outperforms state-of-the-art techniques across multiple evaluation metrics. This work lays the groundwork for a new class of adaptable SEM models, accelerating materials discovery by bridging foundational representation learning with real-world imaging needs.
@article{arxiv.2604.05960,
title = {A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis},
author = {Sk Miraj Ahmed and Yuewei Lin and Chuntian Cao and Shinjae Yoo and Xinpei Wu and Won-Il Lee and Nikhil Tiwale and Dan N. Le and Thi Thu Huong Chu and Jiyoung Kim and Kevin G. Yager and Chang-Yong Nam},
journal= {arXiv preprint arXiv:2604.05960},
year = {2026}
}