EM3M：用于微观结构分割与生成的电子显微镜图像数据集
EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation
AI总结：
针对深度学习分析电子显微镜图像缺乏大规模专家标注数据集的问题，引入EM3M数据集，介绍构建过程，提供文本到图像扩散模型，评估分割方法并给出优化基线，推动自动化材料分析研究。
摘要：
定量微观结构表征对材料科学至关重要，电子显微镜图像提供高分辨率见解。但基于深度学习的分析因缺乏大规模、专家标注的公共数据集而受阻。我们引入EM3M，一个用于实例级理解电子显微镜图像的大规模多模态数据集。它包含5,091张高质量电子显微镜图像、约300万个实例分割注释和具有解缠属性的图像级文本描述。数据集通过严格的多阶段策划和验证管道构建，并进行全面统计分析以确保可靠性和可重复性。基于这些策划的图像-文本对，我们进一步提供了一个文本到图像的扩散模型，作为一个可控的数据增强引擎，证明合成增强持续提高下游分割性能。为建立系统基准，我们在EM3M上评估代表性实例分割方法。我们的结果表明，传统的基于检测和基于查询的方法在电子显微镜图像固有的极端实例密度和纹理复杂性方面存在困难。我们还提供了一个优化的基于流的基线，以促进公平比较和未来研究。EM3M数据集（此https URL）、生成引擎（生成：此https URL）和在线演示（分割演示：此https URL）公开可用，以支持自动化材料分析的未来研究。
英文摘要：
Quantitative microstructural characterization is fundamental to materials science, and electron micrographs (EMs) provide indispensable high-resolution insights. However, progress in deep learning-based analysis of EMs has been hampered by the scarcity of large-scale, expert-annotated public datasets. To address this issue, we introduce EM3M, a large-scale and multimodal dataset for instance-level understanding of EMs. EM3M comprises 5,091 high-quality EMs, approximately 3 million instance segmentation annotations, and image-level textual descriptions with disentangled attributes. The dataset is constructed through a rigorous multi-stage curation and validation pipeline, with comprehensive statistical analyses to ensure reliability and reproducibility. Building upon these curated image-text pairs, we further provide a text-to-image diffusion model that serves as a controllable data augmentation engine, demonstrating that synthetic augmentation consistently improves downstream segmentation performance. To establish a systematic benchmark, we evaluate representative instance segmentation methods on EM3M. Our results reveal that conventional detection-based and query-based methods struggle with the extreme instance densities and textural complexities inherent in EMs. We additionally provide an optimized flow-based baseline to facilitate fair comparison and future research. EM3M {Dataset: https://huggingface.co/datasets/UniParser/EM3M}, the generative engine {Generation: https://huggingface.co/UniParser/EM3M-Gen}, and an online demo {Segmentation demo: https://www.bohrium.com/apps/uni-aims} are publicly available to support future research in automated materials analysis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
