CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis

TL;DR

CreativeGAN is a novel method that enhances GANs to generate truly unique and innovative designs by identifying and modifying components that contribute to design novelty, supporting automated creative design synthesis.

Contribution

It introduces a new approach combining novelty detection, segmentation, and rewriting to enable GANs to produce more creative and unique designs without human intervention.

Findings

Successfully generated novel bicycle designs with unique features.

Generalized rare design novelties across a broad set of designs.

Demonstrated automated, intervention-free creative design synthesis.

Abstract

Modern machine learning techniques, such as deep neural networks, are transforming many disciplines ranging from image recognition to language understanding, by uncovering patterns in big data and making accurate predictions. They have also shown promising results for synthesizing new designs, which is crucial for creating products and enabling innovation. Generative models, including generative adversarial networks (GANs), have proven to be effective for design synthesis with applications ranging from product design to metamaterial design. These automated computational design methods can support human designers, who typically create designs by a time-consuming process of iteratively exploring ideas using experience and heuristics. However, there are still challenges remaining in automatically synthesizing `creative' designs. GAN models, however, are not capable of generating unique designs, a key to innovation and a major gap in AI-based design automation applications. This paper proposes an automated method, named CreativeGAN, for generating novel designs. It does so by identifying components that make a design unique and modifying a GAN model such that it becomes more likely to generate designs with identified unique components. The method combines state-of-art novelty detection, segmentation, novelty localization, rewriting, and generative models for creative design synthesis. Using a dataset of bicycle designs, we demonstrate that the method can create new bicycle designs with unique frames and handles, and generalize rare novelties to a broad set of designs. Our automated method requires no human intervention and demonstrates a way to rethink creative design synthesis and exploration.