Abstract
Generative Adversarial Networks (GANs) have shown stupendous power in generating realistic images to an extend that human eyes are not capable of recognizing them as synthesized. State-of-the-art GAN models are capable of generating realistic and high-quality images, which promise unprecedented opportunities for generating design concepts. Yet, the preliminary experiments reported in this paper shed light on a fundamental limitation of GANs for generative design: lack of novelty and diversity in generated samples. This article conducts a generative design study on a large-scale sneaker dataset based on StyleGAN, a state-of-the-art GAN architecture, to advance the understanding of the performance of these generative models in generating novel and diverse samples (i.e., sneaker images). The findings reveal that although StyleGAN can generate samples with quality and realism, the generated and style-mixed samples highly resemble the training dataset (i.e., existing sneakers). This article aims to provide future research directions and insights for the engineering design community to further realize the untapped potentials of GANs for generative design.
Original language | English (US) |
---|---|
Pages (from-to) | 633-643 |
Number of pages | 11 |
Journal | Proceedings of the Design Society |
Volume | 3 |
DOIs | |
State | Published - 2023 |
Externally published | Yes |
Event | 24th International Conference on Engineering Design, ICED 2023 - Bordeaux, France Duration: Jul 24 2023 → Jul 28 2023 |
All Science Journal Classification (ASJC) codes
- Computer Graphics and Computer-Aided Design
- Computer Science Applications
- Software
- Modeling and Simulation
Keywords
- Artificial intelligence
- Generative adversarial networks
- Generative design
- Machine learning
- User centred design