Microstructure synthesis using style-based generative adversarial network

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.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• A Learned Representation For Artistic Style
• DOLFIN: Automated Finite Element Computing
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• Modeling Heterogeneous Materials via Two-Point Correlation Functions: I. Basic Principles
• A Superior Descriptor of Random Textures and Its Predictive Capacity
• Modeling Heterogeneous Materials via Two-Point Correlation Functions: II. Algorithmic Details and Applications
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• Inferring low-dimensional microstructure representations using convolutional neural networks
• Aperiodic compression and reconstruction of real world material systems based on Wang tiles
• A jigsaw puzzle framework for homogenization of high porosity foams

Cited by in corpus (4)

• Deep learning for synthetic microstructure generation in a materials-by-design framework for heterogeneous energetic materials
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics
• Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions
• 3DMaterialGAN: Learning 3D Shape Representation from Latent Space for Materials Science Applications