EM3M

# EM3M <p align="center"> <img src="./em3m.png" width="100%"> </p> <p align="center"> Overview of the UniEM-3M dataset. </p> ## 📘 Dataset Summary UniEM-3M is the first large-scale multimodal electron microscopy (EM) dataset for instance-level microstructural understanding, which is proposed in our paper "[UniEM-3M: A Universal Electron Micrograph Dataset for Microstructural Segmentation and Generation](https://arxiv.org/abs/2508.16239)". It provides high-resolution electron micrographs with expert-curated annotations and textual descriptions, aiming to accelerate research in automated materials analysis and deep learning for materials science. --- ## 🎨 EM3M-Gen We also release **EM3M-Gen**, a text-to-image generation model trained on UniEM-3M for scientific electron micrograph synthesis. 🤗 Hugging Face Model: https://huggingface.co/UniParser/EM3M-Gen It enables controllable generation of electron micrographs from textual descriptions, facilitating data augmentation, generative modeling research, and multimodal learning in materials science. --- ## 🌐 Online Application We trained a **state-of-the-art instance segmentation model** for microstructural characterization on UniEM-3M, and further developed a **complete analysis software suite** based on this model. It is available as an online application here: 👉 [online application](https://www.bohrium.com/apps/uni-aims?tab=readme_link) --- ## 📂 Dataset Structure - **Currently released**: - **data_structured_descriptions**: data with structured descriptions - **data_image_captions**: data with natural language descriptions --- ## 🚀 Applications - Multimodal learning in materials science - Text-to-image generation with scientific fidelity - Instance segmentation of microstructures - Image captioning / attribute-aware description generation - Training and benchmarking deep learning models for EM data --- ## 📖 Citation If you use this dataset, please cite: ```bibtex @article{xia2025uniem, title={UniEM-3M: A Universal Electron Micrograph Dataset for Microstructural Segmentation and Generation}, author={Xia, Zhiyi and Li, Yiming and Tang, Shi and Fan, Zuxin and Fang, Xi and Tao, Haoyi and Cai, Xiaochen and Ke, Guolin and Zhang, Linfeng and Hong, Yanhui and others}, journal={arXiv preprint arXiv:2508.16239}, year={2025} }