mlsanityData to 7 Oct 2026

Generative Image Restoration and Super-Resolution using Physics-Informed Synthetic Data for Scanning Tunneling Microscopy

arXiv 2510.25921 ↗First posted 29 Oct 2025cs.CV cond-mat.mtrl-scicited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Scanning tunnelling microscopy (STM) enables atomic-resolution imaging and atom manipulation, but its utility is often limited by tip degradation and slow serial data acquisition. Fabrication adds another layer of complexity since the tip is often subjected to large voltages, which may alter the shape of its apex, requiring it to be conditioned. Here, we propose a machine learning (ML) approach for image repair and super-resolution to alleviate both challenges. Using a dataset of only 36 pristine experimental images of Si(001):H, we demonstrate that a physics-informed synthetic data generation pipeline can be used to train several state-of-the-art flow-matching and diffusion models. Quantitative evaluation with metrics such as the CLIP Maximum Mean Discrepancy (CMMD) score and structural similarity demonstrates that our models are able to effectively restore images and offer a two- to fourfold reduction in image acquisition time by accurately reconstructing images from sparsely sampled data. Our framework has the potential to significantly increase STM experimental throughput by offering a route to reducing the frequency of tip-conditioning procedures and to enhancing frame rates in existing high-speed STM systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 17 of its 41 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

17 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution15 Mar

Other references · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  10. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  11. 2021Fourier Space Losses for Efficient Perceptual Image Super-Resolutioncited by 72
  12. 2022A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysiscited by 24
4 more
  1. 2025Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathwayscited by 17
  2. 2020Autonomous robotic nanofabrication with reinforcement learningcited by 8
  3. 2019Embedding Human Heuristics in Machine-Learning-Enabled Probe Microscopycited by 2
  4. 2024Physics-augmented Deep Learning with Adversarial Domain Adaptation: Applications to STM Image Denoisingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology
  2. 2026From Artefact to Insight: Efficient Low-Rank Adaptation of BrushNet for Scanning Probe Microscopy Image Restoration
  3. 2026A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis
  4. 2025Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model
  5. 2026Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion Augmentation
  6. 2024Addressing Class Imbalance and Data Limitations in Advanced Node Semiconductor Defect Inspection: A Generative Approach for SEM Images
  7. 2025AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use
  8. 2026SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy