Portal de Periódicos da CAPES

Microstructure synthesis using style-based generative adversarial networks

2020; American Physical Society; Volume: 101; Issue: 4 Linguagem: Inglês

10.1103/physreve.101.043308

2470-0061

Daria Fokina, Ekaterina Muravleva, George Ovchinnikov, Ivan Oseledets,

Computer Graphics and Visualization Techniques

This 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.