Generation of highly realistic microstructural images of alloys from limited data with a style-based generative adversarial network
Abstract In materials science, the amount of observational data is often limited by operating protocols that require a high level of expertise, often machine-dependent, developed for a time-consuming integration of valuable data. Scanning electron microscopy (SEM) is one of those methodologies of ch...
Main Authors: | Guillaume Lambard, Kazuhiko Yamazaki, Masahiko Demura |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-01-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-27574-8 |
Similar Items
-
Synthesizing realistic high-resolution retina image by style-based generative adversarial network and its utilization
by: Mingyu Kim, et al.
Published: (2022-10-01) -
Image Captioning with Style Using Generative Adversarial Networks
by: Dennis Setiawan, et al.
Published: (2022-03-01) -
CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis
by: Abdallah Alshantti, et al.
Published: (2024-01-01) -
Image Steganography and Style Transformation Based on Generative Adversarial Network
by: Li Li, et al.
Published: (2024-02-01) -
Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images
by: Abid Khan, et al.
Published: (2023-05-01)