Generation of highly realistic microstructural images of alloys from limited data with a style-based generative adversarial network

HIGHLIGHTS

• who: Guillaume Lambard from the National Institute have published the article: Generation of highly realistic microstructural images of alloys from limited data with a style-based generative adversarial network, in the Journal: Scientific Reports Scientific Reports
• what: The authors show that the StyleGAN2 architecture trained with the ADA protocol is a viable tool for generating high-quality and diverse 512 u00d7 512 SEM images of ferrite-martensite DP steel alloy in low data regime, with a mild change in the training strategy in comparison to its application to FFHQ images of human faces. The authors . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.