Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.05960 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915921344331776 |
|---|---|
| author | Ahmed, Sk Miraj Lin, Yuewei Cao, Chuntian Yoo, Shinjae Wu, Xinpei Lee, Won-Il Tiwale, Nikhil Le, Dan N. Chu, Thi Thu Huong Kim, Jiyoung Yager, Kevin G. Nam, Chang-Yong |
| author_facet | Ahmed, Sk Miraj Lin, Yuewei Cao, Chuntian Yoo, Shinjae Wu, Xinpei Lee, Won-Il Tiwale, Nikhil Le, Dan N. Chu, Thi Thu Huong Kim, Jiyoung Yager, Kevin G. Nam, Chang-Yong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05960 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis Ahmed, Sk Miraj Lin, Yuewei Cao, Chuntian Yoo, Shinjae Wu, Xinpei Lee, Won-Il Tiwale, Nikhil Le, Dan N. Chu, Thi Thu Huong Kim, Jiyoung Yager, Kevin G. Nam, Chang-Yong Machine Learning 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. |
| title | A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.05960 |