id |
ecaade2022_203 |
authors |
Kim, Frederick Chando and Huang, Jeffrey |
year |
2022 |
title |
Perspectival GAN - Architectural form-making through dimensional transformation |
source |
Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 341–350 |
doi |
https://doi.org/10.52842/conf.ecaade.2022.1.341
|
summary |
With the ascendance of Generative Adversarial Networks (GAN), promising prospects have arisen from the abilities of machines to learn and recognize patterns in 2D datasets and generate new results as an inspirational tool in architectural design. Insofar as the majority of ML experiments in architecture are conducted with imagery based on readily available 2D data, architects and designers are faced with the challenge of transforming machine-generated images into 3D. On the other hand, GAN-generated images are found to be able to learn the 3D information out of 2D perspectival images. To facilitate such transformation from 2D and 3D data in the framework of deep learning in architecture, this paper explores making new architectural forms from flat GAN images by employing traditional tools of projective geometry. The experiments draw on Brook Taylor’s 19th- century theorem of inverse projection system for creating architectural form from perspectival information learned from GAN images of Swiss alpine architecture. The research develops a parametric tool that automates the dimensional transformation of 2D images into 3D architectural forms. This research identifies potential synergic interactions between traditional tools and techniques of architects and deep learning algorithms to achieve collective intelligence in designing and representing creative architecture forms between humans and machines. |
keywords |
Machine Learning, GAN, Architectural Form, Perspective Projection, Inverse Perspective, Digital Representation |
series |
eCAADe |
email |
frederick.kim@epfl.ch |
full text |
file.pdf (2,653,392 bytes) |
references |
Content-type: text/plain
|
Andersen, K. (1992)
Brook Taylors Work on Linear Perspective: A Study of Taylors Role in the History of Perspective Geometry
, Including Facsimiles of Taylor's Two Books on Perspective. New York: Springer-Verlag (Sources in the History of Mathematics and Physical Sciences). doi:10.1007/978-1-4612-0935-5
|
|
|
|
Bachl, M. and Ferreira, D.C. (2020)
City-GAN: Learning architectural styles using a custom Conditional GAN architecture
, arXiv:1907.05280 [cs, eess, stat] [Preprint]. Available at: http://arxiv.org/abs/1907.05280 (Accessed: 30 March 2022)
|
|
|
|
Carpo, M. (2013)
The Art of Drawing
, Architectural Design, 83, pp. 128-133
|
|
|
|
Cohen, P.S. (2001)
Contested Symmetries: And Other Predicaments in Architecture
, Princeton Architectural Press
|
|
|
|
del Campo, M. and Leach, N. (2022)
Unleashing New Creativities
, Architectural Design, 92(3), pp. 122-135. doi:https://doi.org/10.1002/ad.2823
|
|
|
|
del Campo, M. (2021)
Architecture, Language and AI - Language,Attentional Generative Adversarial Networks (AttnGAN) and Architecture Design
, A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 211-220. CUMINCAD. Available at: http://papers.cumincad.org/cgi-bin/works/2015%20+dave=2:/Show?caadria2021_389 (Accessed: 5 January 2022)
|
|
|
|
Goodfellow, I., Bengio, Y. and Courville, A. (2016)
Deep Learning
, MIT Press
|
|
|
|
Goodfellow, I. (2017)
NIPS 2016 Tutorial: Generative Adversarial Networks
, arXiv:1701.00160 [cs] [Preprint]. Available at: http://arxiv.org/abs/1701.00160 (Accessed: 1 April 2022)
|
|
|
|
Healy, A.F. et al. (2003)
Handbook of Psychology
, Experimental Psychology. John Wiley & Sons
|
|
|
|
Huang, J. et al. (2021)
On GANs, NLP and Architecture: Combining Human and Machine Intelligences for the Generation and Evaluation of Meaningful Designs
, Technology|Architecture + Design, 5(2), pp. 207-224. doi:10.1080/24751448.2021.1967060
|
|
|
|
Newton, D. (2019)
Generative Deep Learning in Architectural Design
, Technology|Architecture + Design, 3(2), pp. 176-189. doi:10.1080/24751448.2019.1640536
|
|
|
|
Steinfeld, K. (2019)
GAN Loci
, ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided DesignArchitecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at AustSchool of Architecture, Austin, Texas 21-26 October, 2019) pp. 392-403. CUMINCAD. Available at: http://papers.cumincad.org/cgi-bin/works/paper/acadia19_392 (Accessed: 30 March 2022)
|
|
|
|
Wu, C. (2021)
The geometry of the cone, from Descartes to Grasshopper
, Ideabooks.it, 16 June. Available at: https://www.ideabooks.it/prodotto/domus-1058/ (Accessed: 17 March 2022)
|
|
|
|
Zhang, H. et al. (2019)
Self-Attention Generative Adversarial Networks
, arXiv:1805.08318 [cs, stat] [Preprint]. Available at: http://arxiv.org/abs/1805.08318 (Accessed: 30 March 2022)
|
|
|
|
Zhang, H. (2019)
3D Model Generation on Architectural Plan and Section Training through Machine Learning
, Technologies, 7(4), p. 82. doi:10.3390/technologies7040082
|
|
|
|
last changed |
2024/04/22 07:10 |
|