id |
caadria2024_325 |
authors |
Kim, Dongyun and Kim, Hanjun |
year |
2024 |
title |
Territorial Sabotage: From Tracing Seoul’s Possibilities to Recompositing Its Urban Identity |
source |
Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 159–168 |
doi |
https://doi.org/10.52842/conf.caadria.2024.2.159
|
summary |
This paper explores the evolution of architecture within an urban scale, utilizing Generative Adversarial Networks (GANs) to increase diversity and suggest various alternatives. Drawing inspiration from Henri Bergson's concepts of creative evolution, GANs' non-deterministic nature echoes Bergson's emphasis on creativity within evolutionary processes in urban design. Leveraging GANs' latent space, this study envisions a framework for AI-driven architectural generation, merging Bergson's ideas of creative intuition with AI's adaptive potential. Using Seoul as a case study, integrating Kevin Lynch's principles and symbolic representation techniques like the Nolli map, the research navigates urban spaces to create cohesive morphologies. Employing 2D GAN-based analysis and integrating 3D GAN, the study discerns urban layouts and building configurations. Additional diffusion models refine the 3D GAN outputs, expediting rendering and visualization phases, suggesting an innovative, data-driven architectural design methodology. By amalgamating diverse AI models into a cohesive workflow, it blends traditional architectural wisdom with cutting-edge computational capabilities, heralding a paradigm shift in architectural innovation. |
keywords |
Generative Adversarial Networks, 3D GAN, Stable Diffusion, Cartography, Nolli map |
series |
CAADRIA |
email |
|
full text |
file.pdf (2,842,396 bytes) |
references |
Content-type: text/plain
|
Bergson, H. (2003)
Creative Evolution (A
, Mitchell, Trans.). Dover Publications
|
|
|
|
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014)
Generative Adversarial Nets
, ArXiv.org. https://arxiv.org/abs/1406.2661
|
|
|
|
Ji, H., & Ding, W. (2021)
Mapping urban public spaces based on the Nolli map method
, Frontiers of Architectural Research, 10(3), 540-554. https://doi.org/10.1016/j.foar.2021.04.001
|
|
|
|
Karras, T., Laine, S., & Aila, T. (2020)
A style-based generator architecture for generative adversarial networks
, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1-1. https://doi.org/10.1109/TPAMI.2020.2970919
|
|
|
|
Karras, T., Miika Aittala, Janne Hellsten, Laine, S., Lehtinen, J., & Timo Aila. (2020)
Training generative adversarial networks with limited data
, CoRR, abs/2006.06676. https://arxiv.org/abs/2006.06676
|
|
|
|
Kim, D., Lloyd Sukgyo Lee, & Kim, H. (2023)
Elemental Sabotage: Diffusing Functional Morphologies
, Proceedings of the 28th CAADRIA Conference, 29-38. https://doi.org/10.52842/conf.caadria.2023.1.029
|
|
|
|
Kim, D. (2023)
Latent morphologies: Encoding architectural features and decoding their structure through artificial intelligence
, International Journal of Architectural Computing. https://doi.org/10.1177/14780771231209458
|
|
|
|
Lynch, K. (1960)
The image of the city
, (pp 46-49). The MIT Press
|
|
|
|
Mitchel, W. J. (1997)
City of bits : Space, palce and the infobahn
, The MIT Press
|
|
|
|
Radford, A., Metz, L., & Chintala, S. (2016)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
, ArXiv.org. https://arxiv.org/abs/1511.06434v2
|
|
|
|
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Björn Ommer. (2021)
High-resolution image synthesis with latent diffusion models
, CoRR, abs/2112.10752. https://arxiv.org/abs/2112.10752
|
|
|
|
Rossi, A. (1982)
The architecture of the city
, (pp 130-133). The MIT Press
|
|
|
|
last changed |
2024/11/17 22:05 |
|