Quantitative microstructural characterization is fundamental to materials science, where electron micrograph (EM) provides indispensable high-resolution insights. However, progress in deep learning-based EM characterization has been hampered by the scarcity of large-scale, diverse, and expert-annotated datasets, due to acquisition costs, privacy concerns, and annotation complexity. To address this issue, we introduce UniEM-3M, the first large-scale and multimodal EM dataset for instance-level understanding. It comprises 5,091 high-resolution EMs, about 3 million instance segmentation labels, and image-level attribute-disentangled textual descriptions, a subset of which will be made publicly available. Furthermore, we are also releasing a text-to-image diffusion model trained on the entire collection to serve as both a powerful data augmentation tool and a proxy for the complete data distribution. To establish a rigorous benchmark, we evaluate various representative instance segmentation methods on the complete UniEM-3M and present UniEM-Net as a strong baseline model. Quantitative experiments demonstrate that this flow-based model outperforms other advanced methods on this challenging benchmark. Our multifaceted release of a partial dataset, a generative model, and a comprehensive benchmark -- available at huggingface -- will significantly accelerate progress in automated materials analysis.
@article{arxiv.2508.16239,
title = {UniEM-3M: A Universal Electron Micrograph Dataset for Microstructural Segmentation and Generation},
author = {Nan wang and Zhiyi Xia and Yiming Li and Shi Tang and Zuxin Fan and Xi Fang and Haoyi Tao and Xiaochen Cai and Guolin Ke and Linfeng Zhang and Yanhui Hong},
journal= {arXiv preprint arXiv:2508.16239},
year = {2025}
}