DCG-GAN: design concept generation with generative adversarial networks

Generative adversarial networks (GANs) have recently been proposed as a potentially disruptive approach to generative design due to their remarkable ability to generate visually appealing and realistic samples. Yet, we show that the current generator-discriminator architecture inherently limits the...

Full description

Saved in:
Bibliographic Details
Published inDesign Science Vol. 10
Main Authors Ghasemi, Parisa, Yuan, Chenxi, Marion, Tucker, Moghaddam, Mohsen
Format Journal Article
LanguageEnglish
Published Cambridge, UK Cambridge University Press 18.09.2024
Subjects
Artificial intelligence
Automation
Creativity
Datasets
Design
Design concept generation
Design engineering
Designers
Diversity
Efficiency
Generative adversarial networks
Mathematical functions
Methods
Novelty
Semantics
Generative adversarial networks
Design concept generation
Creativity
Diversity
Novelty
Online AccessGet full text

Cover

More Information
Summary:Generative adversarial networks (GANs) have recently been proposed as a potentially disruptive approach to generative design due to their remarkable ability to generate visually appealing and realistic samples. Yet, we show that the current generator-discriminator architecture inherently limits the ability of GANs as a design concept generation (DCG) tool. Specifically, we conduct a DCG study on a large-scale dataset based on a GAN architecture to advance the understanding of the performance of these generative models in generating novel and diverse samples. Our findings, derived from a series of comprehensive and objective assessments, reveal that while the traditional GAN architecture can generate realistic samples, the generated and style-mixed samples closely resemble the training dataset, exhibiting significantly low creativity. We propose a new generic architecture for DCG with GANs (DCG-GAN) that enables GAN-based generative processes to be guided by geometric conditions and criteria such as novelty, diversity and desirability. We validate the performance of the DCG-GAN model through a rigorous quantitative assessment procedure and an extensive qualitative assessment involving 89 participants. We conclude by providing several future research directions and insights for the engineering design community to realize the untapped potential of GANs for DCG.
ISSN:2053-4701
2053-4701
DOI:10.1017/dsj.2024.13