mlsanityData to 7 Oct 2026

High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology

arXiv 2606.24817 ↗First posted 23 Jun 2026cs.CV eess.IVcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 23 of its 39 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

23 of 39 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model21 Apr
  2. 2024Addressing Class Imbalance and Data Limitations in Advanced Node Semiconductor Defect Inspection: A Generative Approach for SEM Images14 Jul
  3. 2023SEMI-DiffusionInst: A Diffusion Model Based Approach for Semiconductor Defect Classification and Segmentation17 Jul

Other references · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  9. 2018Demystifying MMD GANscited by 1,268
  10. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  11. 2023Efficient Diffusion Training via Min-SNR Weighting Strategycited by 242
  12. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
8 more
  1. 2015Learning to Generate Images with Perceptual Similarity Metricscited by 39
  2. 2024DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cutcited by 26
  3. 2021Realistic galaxy image simulation via score-based generative modelscited by 24
  4. 2023Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy imagescited by 8
  5. 2024Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopycited by 5
  6. 2023Deep Learning of Crystalline Defects from TEM images: A Solution for the Problem of "Never Enough Training Data"cited by 4
  7. 2023A robust synthetic data generation framework for machine learning in High-Resolution Transmission Electron Microscopy (HRTEM)cited by 3
  8. 2024Towards Improved Semiconductor Defect Inspection for high-NA EUVL based on SEMI-SuperYOLO-NAScited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion Augmentation
  2. 2026A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis
  3. 2025Generative Image Restoration and Super-Resolution using Physics-Informed Synthetic Data for Scanning Tunneling Microscopy
  4. 2026Frequency-Aware Dual-Stream Learning for Balanced Realism and Fidelity in Electron Microscopy Imaging
  5. 2025Parameter-aware high-fidelity microstructure generation using stable diffusion
  6. 2023Reference-Free Isotropic 3D EM Reconstruction using Diffusion Models
  7. 2024Denoising diffusion models for high-resolution microscopy image restoration
  8. 2025DIFFRACT: Diffusion-based Restoration via Adaptive Control and Thresholding for Diffraction Imaging