# Microstructure synthesis using style-based generative adversarial network

arXiv: https://arxiv.org/abs/1909.07042 · HTML: https://mlsanity.com/paper/1909.07042/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics](https://mlsanity.com/paper/2206.01693/) (2022)
- [Multi-plane denoising diffusion-based dimensionality expansion for 2D-to-3D reconstruction of microstructures with harmonized sampling](https://mlsanity.com/paper/2308.14035/) (2023)
- [A Generative Model for Accelerated Inverse Modelling Using a Novel Embedding for Continuous Variables](https://mlsanity.com/paper/2311.11343/) (2023)
- [AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design](https://mlsanity.com/paper/2603.27195/) (2026)
- [Microstructure reconstruction via artificial neural networks: A combination of causal and non-causal approach](https://mlsanity.com/paper/2110.09815/) (2021)
- [Towards Microstructural State Variables in Materials Systems](https://mlsanity.com/paper/2301.04261/) (2023)
- [Denoising diffusion-based synthetic generation of three-dimensional (3D) anisotropic microstructures from two-dimensional (2D) micrographs](https://mlsanity.com/paper/2312.07832/) (2023)

## Abstract (arXiv)

Work considers the usage of StyleGAN architecture for the task of microstructure synthesis. The task is the following: given number of samples of structure we try to generate similar samples at the same time preserving its properties. Since the considered architecture is not able to produce samples of sizes larger than the training images, we propose to use image quilting to merge fixed-sized samples. One of the key features of the considered architecture is that it uses multiple image resolutions. We also investigate the necessity of such an approach.