| id |
caadria2024_300 |
| authors |
Mao, Yujun, Peng, Wenzhe and Nagakura, Takehiko |
| year |
2024 |
| title |
Pseudo-cross-modal Translation: Bridging Architectural Plan and Perspective through a pix2pix Network |
| 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 1, pp. 179–188 |
| doi |
https://doi.org/10.52842/conf.caadria.2024.1.179
|
| summary |
Architectural pedagogy often segments designs into diverse representation forms like plans and renderings. With AI's growing influence on early design through GANs, Midjourney, and Stable Diffusion, there remains a gap in translating between diverse architectural representations, a phenomenon we term 'Pseudo-cross-modal Translation', indicating the indirect transformation between non-analogous architectural representations. Addressing this, our research hypotheses a practical need and actionable possibility to translate architectural plans into perspective renderings via neural networks, exploiting the information differences between them. We navigate this intricate translation utilising a pix2pix network of which the dataset encompasses plans with designated view cones and corresponding rendered perspectives. The training data are sampled from the model of Mies van der Rohe’s Barcelona Pavilion and its variations. Evaluations through perceptual surveys, which incorporate modifications in information complexity of plans, illuminate the neural networks' nuanced capability to bridge plans and perspectives under various conditions. Our results not only validate this translation but also spotlight the computational statistics' latent potential in deciphering unseen spatial features from the variance between plans and perspectives. This work unveils a novel method for generating architectural imagery, promoting a holistic spatial understanding. center8641080 |
| keywords |
Plan, Perspective, pix2pix, Architectural Representation |
| series |
CAADRIA |
| email |
|
| full text |
 file.pdf (780,821 bytes) |
| references |
Content-type: text/plain
|
Coons, S. A. (1963)
 An outline of the requirements for a computer-aided design system
, Proceedings of the May 21-23, 1963, spring joint computer conference (pp. 299-304)
|
|
|
|
|
d'Espouy, H. (1905)
Greek and Roman Architecture in Classic Drawings
, Translated by Henry Hope Reed., 1999. New York: Dover Publications
|
|
|
|
|
Goodfellow, I. J., Pouget-Abadie, J. Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014)
Generative Adversarial Nets
, Advances in Neural Information Processing Systems 2672-80
|
|
|
|
|
Huang, W., & Zheng, H. (2018)
Architectural drawings recognition and generation through machine learning
, P. Anzalone, M. Del Signore, & A. J. Wit (Eds.), Recalibration: on imprecision and infidelity: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture, ACADIA 2018 (pp. 156-165)
|
|
|
|
|
Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017)
Image-to-image Translation with Conditional Adversarial Networks
, 217 IEEE Conference on Computer Vision and Pattern Recognition (pp.1125-1134) Available at: https://doi.org/1.119/CVPR.217.632
|
|
|
|
|
K. Kuma (2012)
Anti-object: the dissolution and disintegration of architectures
, Reprint., vol. 2. London: Architectural Association Publications
|
|
|
|
|
Koh, I. (2023)
Architectural sampling: three possible preconditions for machine learning architectural forms
, Architecture Intelligence, 2(1), 7
|
|
|
|
|
Nagakura, T. and Oishi, J. (2006)
Deskrama
, Proceedings of ACM SIGGRAPH 1998, Emerging technologies. Article No. 6. New York: ACM New York
|
|
|
|
|
Nagakura, T., & Sung, W. (2014)
Ramalytique: Augmented reality in architectural exhibitions
, Conference on Cultural Heritage and New Technologies 19th Proceedings (pp. 3-5)
|
|
|
|
|
Nagakura, T. (1998)
DIGITARAM
, 17th Exhibition of Winning Architectural Models and Drawing. SD Review, December 1998, pp.36-38
|
|
|
|
|
Palladio, A. (1570)
The Four Books on Architecture
, Translated by Robert Tavernor and Richard Schofield., 1997. Cambridge, Massachusetts: MIT Press
|
|
|
|
|
Rossi, G., & Nicholas, P. (2021)
Encoded Images: Representational protocols for integrating cGANs in iterative computational design processes
, Acadia 2020 Distributed Proximities: Proceedings of the 40th Annual Conference of the Association for Computer Aided Design in Architecture (Vol. 1, pp. 218-227)
|
|
|
|
|
Steinfeld, K. (2019)
Gan Loci
, Proceedings of 39th Conference of the Association for Computer Aided Design in Architecture: Ubiquity and Autonomy (pp. 392-403)
|
|
|
|
|
Vesely, D. (2004)
Architecture in the age of divided representation: the question of creativity in the shadow of production
, MIT press
|
|
|
|
| last changed |
2024/11/17 22:05 |
|
