%0 Conference Paper
%A Nobari, A.H.
%A Rashad, M.F.
%A Ahmed, F.
%D 2021
%F scholars:15729
%I American Society of Mechanical Engineers (ASME)
%K 3D modeling; Automation; Computer aided design; Deep neural networks; Generative adversarial networks; Heuristic methods; Image recognition; Metadata; Product design, Accurate prediction; Automated methods; Computational design methods; Creative design; Design automations; Design synthesis; Generative model; Language understanding; Machine learning techniques; Network models, Iterative methods
%R 10.1115/DETC2021-68103
%T Creativegan: Editing generative adversarial networks for creative design synthesis
%U https://khub.utp.edu.my/scholars/15729/
%V 3A-202
%X 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. For details and code used in this paper please refer to http://decode.mit.edu/projects/creativegan/. Copyright © 2021 by ASME.
%Z cited By 6; Conference of 47th Design Automation Conference, DAC 2021, Held as Part of the ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2021 ; Conference Date: 17 August 2021 Through 19 August 2021; Conference Code:174204