Architectural Form Explorations through Generative Adversarial Networks: Predicting the potentials of StyleGAN


Eroğlu R., Gül L. F.

40th Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2022, Ghent, Belgium, 13 - 16 September 2022, vol.2, pp.575-582 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 2
  • City: Ghent
  • Country: Belgium
  • Page Numbers: pp.575-582
  • Istanbul Technical University Affiliated: Yes

Abstract

© 2022, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.In recent years, generative models have been rapidly transforming into a broad field of research, and artificial intelligence (AI) works are increasing. Since deep learning technologies such as Generative Adversarial Networks (GANs) providing synthesized new images are becoming more accessible, researchers in the design and related fields are very much interested in adapting GANs into practice. Especially, StyleGAN has a strong capability for image learning, reconstruction simulation, and absorbing the pixel characteristics of images in the input dataset. StyleGAN also produces similar imitation outputs and summarizes all the input data into one "average output". The study aims to reveal the potential of these outputs that can be employed as a visual inspiration aid for designers. This article will discuss the outputs of the experiments, findings, and prospects of StyleGAN. Keywords: Artificial Intelligence, Machine Learning, Generative Adversarial Networks, StyleGAN.