用15张图训练出高保真电子显微镜合成图像，解决半导体检测数据少的难题。
High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology
- 基于扩散模型，用15张样本分阶段生成全尺寸图像。
- 合成图像结构相似度超0.98，与真实图像专家评估一致。
- 适合半导体缺陷检测、分割等下游任务的数据增强。
先进半导体节点大幅增加了对透射电子显微镜（TEM）的需求，但破坏性样品制备、成像速度慢和成本高严重限制了用于下游机器学习（ML）的多样化数据集的可用性。合成数据生成变得至关重要，但现有生成模型常忽略TEM特有的噪声、结构细节和随机变异性，影响评估效果。本文提出一种去噪扩散概率模型（DDPM）框架，在极端数据稀缺下生成合成TEM图像。采用渐进式块状训练策略，从低分辨率块逐步扩展到全图，仅需15个样本即可从零开始训练。集成自定义TrivialAugment改进、跨工艺域迁移、分类器引导及RePaint风格修复，最终生成保留全局结构与空间关系的完整图像，符合晶圆厂计量要求。此外，将DDPM特征表示用于分割，通过分割编码器特征图获得连贯区域掩码。合成图像达到最高MS-SSIM > 0.98，且定性专家评估与结构相似性结果一致，可有效支持缺陷检测、分割和计量等下游机器学习任务，同时保持统计与物理真实性。
原文摘要 · Abstract (English)
Advanced semiconductor nodes drastically increased demand for Transmission Electron Microscopy (TEM), yet destructive sample preparation, slow imaging and high costs severely limit the availability of diverse datasets needed for downstream machine learning (ML). Synthetic data generation is becoming essential, but current generative models often miss TEM-specific noise, structural detail, and stochastic variability crucial for evaluation. We present a Denoising Diffusion Probabilistic Model (DDPM) framework for synthetic TEM image generation under extreme data scarcity. A progressive patch-based training strategy scales from low-resolution patches to full images, enabling from-scratch training with only 15 samples. We integrate a custom TrivialAugment adaptation, cross-process domain transfer, classifier guidance, and RePaint-style inpainting, culminating in full-image generation that preserves global structural and spatial relationships in compliance with FAB metrology requirements. Beyond synthesis, we repurpose DDPM feature representations for segmentation, partitioning encoder feature maps to obtain coherent region masks. Our synthetic images achieve up to MS-SSIM > 0.98 and qualitative expert assessment consistent with structural similarity results, facilitating downstream ML training for defect detection, segmentation, and metrology while preserving statistical and physical realism.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。