Microstructure synthesis using style-based generative adversarial network

TL;DR

This paper explores using StyleGAN for microstructure synthesis, combining it with image quilting to generate larger samples while analyzing the importance of multi-resolution features.

Contribution

It introduces a method that integrates StyleGAN with image quilting to synthesize larger microstructure samples, addressing size limitations.

Findings

StyleGAN can generate microstructure samples with preserved properties.

Image quilting enables creation of larger samples from fixed-sized outputs.

Multi-resolution features impact synthesis quality.

Abstract

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.