# Microstructure reconstruction of 2D/3D random materials via diffusion-based deep generative models

arXiv: https://arxiv.org/abs/2311.17319 · HTML: https://mlsanity.com/paper/2311.17319/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2023.

## Built on by (most cited first, 9 of 9)

- [AI-driven inverse design of materials: Past, present and future](https://mlsanity.com/paper/2411.09429/) (2024)
- [Deep learning-aided inverse design of porous metamaterials](https://mlsanity.com/paper/2507.17907/) (2025)
- [Equilibrium Conserving Neural Operators for Super-Resolution Learning](https://mlsanity.com/paper/2504.13422/) (2025)
- [Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling](https://mlsanity.com/paper/2505.01917/) (2025)
- [Predicting Stress in Two-phase Random Materials and Super-Resolution Method for Stress Images by Embedding Physical Information](https://mlsanity.com/paper/2504.18854/) (2025)
- [Analysis of the Compaction Behavior of Textile Reinforcements in Low-Resolution In-Situ CT Scans via Machine-Learning and Descriptor-Based Methods](https://mlsanity.com/paper/2508.10943/) (2025)
- [Data-efficient Bayesian-guided design selection from large candidate sets: Application to hyperelastic stochastic metamaterials](https://mlsanity.com/paper/2603.15917/) (2026)
- [GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction](https://mlsanity.com/paper/2605.03764/) (2026)
- [Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model](https://mlsanity.com/paper/2609.20358/) (2026)

## Abstract (arXiv)

Microstructure reconstruction serves as a crucial foundation for establishing Process-Structure-Property (PSP) relationship in material design. Confronting the limitations of variational autoencoder and generative adversarial network within generative modeling, this study adopted the denoising diffusion probability model (DDPM) to learn the probability distribution of high-dimensional raw data and successfully reconstructed the microstructures of various composite materials, such as inclusion materials, spinodal decomposition materials, chessboard materials, fractal noise materials, and so on. The quality of generated microstructure was evaluated using quantitative measures like spatial correlation functions and Fourier descriptor. On this basis, this study also successfully achieved the regulation of microstructure randomness and the generation of gradient materials through continuous interpolation in latent space using denoising diffusion implicit model (DDIM). Furthermore, the two-dimensional microstructure reconstruction is extended to three-dimensional framework and integrates permeability as a feature encoding embedding. This enables the conditional generation of three-dimensional microstructures for random porous materials within a defined permeability range. The permeabilities of these generated microstructures were further validated through the application of the Boltzmann method.