Blucher Design Proceedings

Dezembro 2020, vol.8, num.4 - XXIV International Conference of the Iberoamerican Society of Digital Graphics
Conference full papers - Open Access Idioma principal | Segundo principal

Machinic Interpolations: A GAN Pipeline for Integrating Lateral Thinking in Computational Tools of Architecture

Machinic Interpolations: A GAN Pipeline for Integrating Lateral Thinking in Computational Tools of Architecture

Asmar, Karen El; Sareen, Harpreet

Conference full papers:

In this paper, we discuss a new tool pipeline that aims to re-integrate lateral thinking strategies in computational tools of architecture. We present a 4-step AI-driven pipeline, based on Generative Adversarial Networks (GANs), that draws from the ability to access the latent space of a machine and use this space as a digital design environment. We demonstrate examples of navigating in this space using vector arithmetic and interpolations as a method to generate a series of images that are then translated to 3D voxel structures. Through a gallery of forms, we show how this series of techniques could result in unexpected spaces and outputs beyond what could be produced by human capability alone.

In this paper, we discuss a new tool pipeline that aims to re-integrate lateral thinking strategies in computational tools of architecture. We present a 4-step AI-driven pipeline, based on Generative Adversarial Networks (GANs), that draws from the ability to access the latent space of a machine and use this space as a digital design environment. We demonstrate examples of navigating in this space using vector arithmetic and interpolations as a method to generate a series of images that are then translated to 3D voxel structures. Through a gallery of forms, we show how this series of techniques could result in unexpected spaces and outputs beyond what could be produced by human capability alone.

Download (PDF)

Palavras-chave:

DOI: 10.5151/sigradi2020-9

Referências bibliográficas
  • [1] Austin, M., & Matthews, L. (2018, January). Drawing imprecision: The digital drawing as bits and pixels. ln Recalibration on lmprecision and lnfidelity-Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture, ACADlA 2018.
  • [2] Avery/GSAPP Architectural Plans and Sections (n.d.) Retrieved from https://www.artstor.org/collection/avery-gsapp- architectural-plans-and-sections-columbia-university/
  • [3] Bono, E. D. (1985). Six Thinking Hats. Little, Brown and Company.
  • [4] Chaillou, S. (2019, July 17). ArchiGAN: a Generative Stack for Apartment Building Design. Retrieved from https://devblogs.nvidia.com/archigan-generative-stack- apartment-building-design/
  • [5] Claypool, M. (2019). The Conference 2019. The Conference 2019. Retrieved from https://www.youtube.com/watch?v=PxAQL7y9wCw
  • [6] Claypool, M. (2020, January 9). The Digital in Architecture: Then, Now and in the Future. Retrieved from https://space10.com/project/digital-in-architecture/
  • [7] Cross, N. (2006). Designerly Ways of Knowing. Springer London. doi:10.1007/1-84628-301-9
  • [8] Dorst, K., & Cross, N. (2001). Creativity in the design process: co- evolution of problem-solution. Design studies, 22(5), 425-437.
  • [9] Huang, W., & Zheng, H. (2018, October). Architectural drawings recognition and generation through machine learning. ln Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADlA), Mexico City, Mexico (pp. 18-20).
  • [10] Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. ln Proceedings of the lEEE Conference on Computer Vision and Pattern Recognition (pp. 4401-4410).
  • [11] Klemmt, C., Pantic, l., Gheorghe A., Sebestyen, A., (2019). Discrete vs. Discretized Growth: Discretized Fabrication of Geometries Generated with Cellular Growth Simulations. ln Proceedings of ACADlA, 2019.
  • [12] Lawson, B. (2006). How designers think: The design process demystified. Routledge.
  • [13] Liu, H., Liao, L., Srivastava, A. (2019). An Anonymous Composition. ln Proceedings of ACADlA, 2019.
  • [14] May, J. (2018). Signal. lmage. Architecture. Columbia University Press.
  • [15] Miller, A. l. (2019). The Artist in the Machine: The World of Al- Powered Creativity. MlT Press.
  • [16] Nauata, N., Chang, K. H., Cheng, C. Y., Mori, G., & Furukawa, Y. (2020). House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation. arXiv preprint arXiv:2003.06988.
  • [17] Newton, D. (2019). Generative Deep Learning in Architectural Design. Technologyl Architecture+ Design, 3(2), 176-189.
  • [18] lsola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). lmage-to- image translation with conditional adversarial networks. ln Proceedings of the lEEE conference on computer vision and pattern recognition (pp. 1125-1134).
  • [19] Retsin, G. (2019). Discrete: Reappraising the Digital in Architecture. John Wiley & Sons.
  • [20] Steenson, M. W. (2017). Architectural lntelligence: How Designers and Architects Created the Digital Landscape. MlT Press. Zhang, H. (2019). 3D Model Generation on Architectural Plan and Section Training through Machine Learning. Technologies, 7(4), 82.
Como citar:

Asmar, Karen El; Sareen, Harpreet; "Machinic Interpolations: A GAN Pipeline for Integrating Lateral Thinking in Computational Tools of Architecture", p-60-66. In: Congreso SIGraDi 2020. São Paulo: Blucher, 2020.
ISSN 23186968, DOI 10.5151/sigradi2020-9

últimos 30 dias

195
downloads

492
visualizações

836
indexações