| id |
ijac202321208 |
| authors |
Ennemoser, Benjamin; Mayrhofer-Hufnagl, Ingrid |
| year |
2023 |
| title |
Design across multi-scale datasets by developing a novel approach to 3DGANs |
| source |
International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 358–373 |
| summary |
The development of Generative Adversarial Networks (GANs) has accelerated the research of Artificial Intelligence (AI) in architecture as a generative tool. However, since their initial invention, many versions have been developed that only focus on 2D image datasets for training and images as output. The current state of 3DGAN research has yielded promising results. However, these contributions focus primarily on building mass, extrusion of 2D plans, or the overall shape of objects. In comparison, our newly developed 3DGAN approach, using fully spatial building datasets, demonstrates that unprecedented interconnections across different scales are possible resulting in unconventional spatial configurations. Unlike a traditional design process, based on analyzing only a few precedents (typology) according to the task, by collaborating with the machine we can draw on a significantly wider variety of buildings across multiple typologies. In addition, the dataset was extended beyond the scale of complete buildings and involved building components that define space. Thus, our results achieve a high spatial diversity. A detailed analysis of the results also revealed new hybrid architectural elements illustrating that the machine continued the interconnections of scale since elements were not explicitly part of the dataset, becoming a true design collaborator. |
| keywords |
3D Generative adversarial networks, architectural design, Spatial Interpolations |
| series |
journal |
| references |
Content-type: text/plain
|
Achlioptas P, Diamanti O, Mitliagkas I, et al (2018)
 Learning representations and generative models for 3D point clouds
, G Jennifer, Dy and A Krause (eds) Proceedings of the 35th international conference on machine learning, ICML 2018, Stockholmsmassan, STH, Sweden, 10-15 July 2018, 80, 40 ¨ –49
|
|
|
|
|
Chaillou S (2019)
AI + architecture: towards a new approach
, Cambridge: Harvard University Graduate School of Design, 2019.
|
|
|
|
|
Chang AX, Funkhouser TA, Guibas LJ, et al (2015)
ShapeNet: an information-rich 3D model repository, 2015
, ArXiv, abs/1512.03012.
|
|
|
|
|
Ching F (2007)
Architecture: form, space, and order
, Hoboken, NJ: John Wiley and Sons, 2007.
|
|
|
|
|
del Campo M, Carlson A and Manninger S (2020)
3D graph convolutional neural networks in architecture design
, Distributed proximities proceedings of the ACADIA conference 2020, 24-30 October, 2020, pp. 688–696.
|
|
|
|
|
del Campo M (2022)
Deep house - datasets, estrangement, and the problem of the new
, ARIN 2022; 1: 12, DOI: 10.1007/s44223-022-00013-w
|
|
|
|
|
Ennemoser B (2022)
Learning to ‘see’ like a machine: artificial intelligence’s impact on the field of architecture
, I Mayrhofer-Hufnagl (ed) Architecture, futurability and the untimely: on the unpredictability of the past. Bielefeld: Transcript Verlag, 2022, pp. 121–137
|
|
|
|
|
Focillon H (1948)
The life of forms in art
, Schultz, NY: Wittenborn, 1948.
|
|
|
|
|
Goodfellow I, Pouget-Abadie J, Mirza M, et al (2014)
Generative adversarial nets
, NIPS 2014; 27: 2672–2680.
|
|
|
|
|
Kim F and Huang J (2022)
Deep architectural archiving (DAA), towards a machine understanding of architectural form
, POST-CARBON-proceedings of the 27th CAADRIA conference, 9-15 April. Sydney: CAADRIA, 2022, pp. 727–736.
|
|
|
|
|
Kleineberg M, Fey M and Frank W (2020)
Adversarial generation of continuous implicit shape representations
, W Alexander and B Francesco (eds) Eurographics 2020 - short papers
|
|
|
|
|
Koh I (2022)
Architectural plasticity: the aesthetics of neural sampling
, AD 2022; 92: 86–93, DOI: 10.1002/ad.2818
|
|
|
|
|
Mildenhall, Ben, Srinivasan, et al (2021)
Nerf: representing scenes as neural radiance fields for view synthesis
, Commun ACM 2021; 65: 99–106.
|
|
|
|
|
Neufert E, Neufert P, Baiche B, et al (2000)
Architects’ data
, 3rd ed. Chichester: Blackwell Science, 2000
|
|
|
|
|
Newton D (2019)
Generative deep learning in architectural design
, Technology|Architecture + Design 2019; 3(2): 176–189.
|
|
|
|
|
Ozel G and Ennemoser B (2019)
Interdisciplinary AI: a machine learning system for streamlining external aesthetic and ¨ cultural influences in architecture
, Proceedings of the 39th annual conference of the association for computer aided design in architecture, 21-26 October. TX: ACADIA Austin, 2019, pp. 380–391.
|
|
|
|
|
Radford A, Metz L and Chintala S (2016)
Unsupervised representation learning with deep convolutional generative adversarial networks, 2016
, ArXiv:1511.06434 [Cs] http://arxiv.org/abs/1511.06434
|
|
|
|
|
Steinfeld K, Park K, Menges A, et al (2019)
Fresh eyes
, JH Lee (ed) Computer-aided architectural design. “Hello, Culture”. CAAD futures 2019, 26-28 June, Daejeon, Korea.
|
|
|
|
|
Taehoon K (2019)
DCGAN in tensorflow
, GitHub repository, 2019, https://github.com/carpedm20/DCGAN-tensorflow
|
|
|
|
|
Tarantola A (2022)
OpenAI releases point-e, which is like dall-E but for 3D modeling
, Engadget 2022; 21,
|
|
|
|
| last changed |
2024/04/17 14:30 |
|
