mlsanityData to 7 Oct 2026

GrainPaint: A multi-scale diffusion-based generative model for microstructure reconstruction of large-scale objects

arXiv 2503.04776 ↗First posted 18 Feb 2025cs.GR cond-mat.mtrl-sci cs.CVcited by 2

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

Abstract (arXiv)

Simulation-based approaches to microstructure generation can suffer from a variety of limitations, such as high memory usage, long computational times, and difficulties in generating complex geometries. Generative machine learning models present a way around these issues, but they have previously been limited by the fixed size of their generation area. We present a new microstructure generation methodology leveraging advances in inpainting using denoising diffusion models to overcome this generation area limitation. We show that microstructures generated with the presented methodology are statistically similar to grain structures generated with a kinetic Monte Carlo simulator, SPPARKS.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 18 of its 82 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

18 of 82 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Multi-plane denoising diffusion-based dimensionality expansion for 2D-to-3D reconstruction of microstructures with harmonized sampling27 Aug
  2. 2023Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties24 Feb

Other references · 16

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  10. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 603
  11. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  12. 2022Understanding Diffusion Models: A Unified Perspectivecited by 337
4 more
  1. 2023Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Modelscited by 61
  2. 2022On the use of Artificial Neural Networks in Topology Optimisationcited by 35
  3. 2021IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structurescited by 19
  4. 2019A Conditional Generative Model for Predicting Material Microstructures from Processing Methodscited by 5

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modelingcited by 1
  2. 2025Phase-fraction guided denoising diffusion model for augmenting multiphase steel microstructure segmentation via micrograph image-mask pair synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Parameter-aware high-fidelity microstructure generation using stable diffusion
  2. 2023Denoising diffusion-based synthetic generation of three-dimensional (3D) anisotropic microstructures from two-dimensional (2D) micrographs
  3. 2025MicroLad: 2D-to-3D Microstructure Reconstruction and Generation via Latent Diffusion and Score Distillation
  4. 2025Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model
  5. 2023Synthesizing realistic sand assemblies with denoising diffusion in latent space
  6. 2024Grand canonical generative diffusion model for crystalline phases and grain boundaries
  7. 2026Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
  8. 2024Structured Pattern Expansion with Diffusion Models