CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis
<jats:title>Abstract</jats:title> <jats:p>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...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ASME International
2023
|
| Online Access: | https://hdl.handle.net/1721.1/150665 |
| _version_ | 1826210578877644800 |
|---|---|
| author | Heyrani Nobari, Amin Rashad, Muhammad Fathy Ahmed, Faez |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Heyrani Nobari, Amin Rashad, Muhammad Fathy Ahmed, Faez |
| author_sort | Heyrani Nobari, Amin |
| collection | MIT |
| description | <jats:title>Abstract</jats:title>
<jats:p>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/.</jats:p> |
| first_indexed | 2024-09-23T14:51:53Z |
| format | Article |
| id | mit-1721.1/150665 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:51:53Z |
| publishDate | 2023 |
| publisher | ASME International |
| record_format | dspace |
| spelling | mit-1721.1/1506652023-05-12T03:12:16Z CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis Heyrani Nobari, Amin Rashad, Muhammad Fathy Ahmed, Faez Massachusetts Institute of Technology. Department of Mechanical Engineering <jats:title>Abstract</jats:title> <jats:p>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/.</jats:p> 2023-05-11T19:47:16Z 2023-05-11T19:47:16Z 2021 2023-05-11T19:45:08Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/150665 Heyrani Nobari, Amin, Rashad, Muhammad Fathy and Ahmed, Faez. 2021. "CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis." Volume 3A: 47th Design Automation Conference (DAC). en 10.1115/DETC2021-68103 Volume 3A: 47th Design Automation Conference (DAC) Creative Commons Attribution-Noncommercial-Share Alike https://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf ASME International arXiv |
| spellingShingle | Heyrani Nobari, Amin Rashad, Muhammad Fathy Ahmed, Faez CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis |
| title | CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis |
| title_full | CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis |
| title_fullStr | CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis |
| title_full_unstemmed | CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis |
| title_short | CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis |
| title_sort | creativegan editing generative adversarial networks for creative design synthesis |
| url | https://hdl.handle.net/1721.1/150665 |
| work_keys_str_mv | AT heyraninobariamin creativeganeditinggenerativeadversarialnetworksforcreativedesignsynthesis AT rashadmuhammadfathy creativeganeditinggenerativeadversarialnetworksforcreativedesignsynthesis AT ahmedfaez creativeganeditinggenerativeadversarialnetworksforcreativedesignsynthesis |