UniParser/UniEM-3M
收藏资源简介:
--- license: mit task_categories: - image-to-text - text-to-image - image-segmentation tags: - electron_micrograph - Materials - microstructure - characterization - scientific_figure_understanding configs: - config_name: default data_files: - split: synthesized_data_structured_descriptions path: data/synthesized_data_structured_descriptions-* - split: synthesized_data_image_captions path: data/synthesized_data_image_captions-* dataset_info: features: - name: image dtype: image - name: attribute_description struct: - name: color_profile dtype: string - name: distribution dtype: string - name: layering dtype: string - name: microscopy_type dtype: string - name: morphology dtype: string - name: particle_density dtype: string - name: pixel_size_profile dtype: string - name: subject dtype: string - name: surface_texture dtype: string - name: full_caption dtype: string splits: - name: synthesized_data_structured_descriptions num_bytes: 13685770890.264 num_examples: 9106 - name: synthesized_data_image_captions num_bytes: 32591407248 num_examples: 19016 download_size: 46275971944 dataset_size: 46277178138.264 size_categories: - 10K<n<100K --- # UniEM-3M ## 📘 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. The dataset addresses the scarcity of large-scale EM datasets by offering: - **5,091** high-resolution EM images - About **3 million instance segmentation labels** - **Image-level structural descriptions** disentangled by attributes - A **text-to-image diffusion model** trained on the full dataset --- ## 🚨 Important Notice At this stage, we are only releasing **the generative model—[UniEM-Gen](https://huggingface.co/NNNan/UniEM-Gen), the generated data and their corresponding textual descriptions**. The **real electron micrographs** and **instance segmentation annotations** will be released after our paper has completed peer review (currently under review). --- ## 🌐 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**: - **synthesized_data_structured_descriptions**: synthesized data with structured descriptions - **synthesized_data_image_captions**: synthesized data with natural language descriptions - **To be released** (after peer review): - Real EM images and corresponding descriptions - ~3M instance segmentation labels --- ## 🚀 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 @misc{wang2025uniem3muniversalelectronmicrograph, 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}, year={2025}, eprint={2508.16239}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2508.16239}, }
license: MIT许可证 task_categories: - 图像到文本(image-to-text) - 文本到图像(text-to-image) - 图像分割(image-segmentation) tags: - 电子显微图(electron_micrograph) - 材料(Materials) - 微观结构(microstructure) - 表征(characterization) - 科学图像理解(scientific_figure_understanding) configs: - 配置名称:默认配置(default) data_files: - split: 合成数据结构化描述(synthesized_data_structured_descriptions) path: data/synthesized_data_structured_descriptions-* - split: 合成数据图像说明(synthesized_data_image_captions) path: data/synthesized_data_image_captions-* dataset_info: features: - 名称:图像(image) 数据类型:图像 - 名称:属性描述(attribute_description) 结构体: - 名称:色彩配置文件(color_profile) 数据类型:字符串 - 名称:分布(distribution) 数据类型:字符串 - 名称:层状结构(layering) 数据类型:字符串 - 名称:显微类型(microscopy_type) 数据类型:字符串 - 名称:形貌(morphology) 数据类型:字符串 - 名称:粒子密度(particle_density) 数据类型:字符串 - 名称:像素尺寸分布(pixel_size_profile) 数据类型:字符串 - 名称:主题(subject) 数据类型:字符串 - 名称:表面纹理(surface_texture) 数据类型:字符串 - 名称:完整说明文本(full_caption) 数据类型:字符串 splits: - 划分名称:合成数据结构化描述(synthesized_data_structured_descriptions) 字节数:13685770890.264 样本数:9106 - 划分名称:合成数据图像说明(synthesized_data_image_captions) 字节数:32591407248 样本数:19016 下载大小:46275971944 数据集总大小:46277178138.264 size_categories: - 10K<n<100K --- # UniEM-3M ## 📘 数据集概述 UniEM-3M是首个用于实例级微观结构理解的大规模多模态电子显微镜(EM)数据集,相关成果发表于论文《UniEM-3M: A Universal Electron Micrograph Dataset for Microstructural Segmentation and Generation》(https://arxiv.org/abs/2508.16239)。 本数据集提供经专家精心标注的高分辨率电子显微图与文本描述,旨在加速材料科学领域自动化材料分析与深度学习相关研究的发展。 本数据集通过提供以下内容,解决了大规模电子显微镜数据集稀缺的问题: - **5091张**高分辨率电子显微镜图像 - 约**300万个**实例分割标注 - 按属性解耦的**图像级结构描述** - 基于全数据集训练的**文本到图像扩散模型(text-to-image diffusion model)** --- ## 🚨 重要声明 现阶段,我们仅发布了**生成式模型——UniEM-Gen(https://huggingface.co/NNNan/UniEM-Gen)、生成数据及其对应的文本描述**。 **真实电子显微图**与**实例分割标注**将在论文完成同行评审(目前处于评审阶段)后发布。 --- ## 🌐 在线应用 我们基于UniEM-3M训练了一款用于微观结构表征的**当前最优实例分割模型**,并基于该模型开发了一套完整的分析软件套件。 该套件现已以在线应用的形式发布:👉 [在线应用程序](https://www.bohrium.com/apps/uni-aims?tab=readme_link) --- ## 📂 数据集结构 - **当前已发布**: - **合成数据结构化描述**:带有结构化描述的合成数据 - **合成数据图像说明**:带有自然语言描述的合成数据 - **待发布**(同行评审通过后): - 真实电子显微镜图像及其对应描述 - 约300万个实例分割标注 --- ## 🚀 应用场景 - 材料科学领域的多模态学习 - 具备科学保真度的文本到图像生成 - 微观结构实例分割 - 图像字幕生成/属性感知描述生成 - 用于电子显微镜数据的深度学习模型训练与基准测试 --- ## 📖 引用格式 若您使用本数据集,请引用以下文献: bibtex @misc{wang2025uniem3muniversalelectronmicrograph, 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}, year={2025}, eprint={2508.16239}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2508.16239}, }




