Artificial imagination of architecture with deep convolutional neural network "Laissez-faire": Loss of control in the esquisse phase

Joaquim Silvestre, Yasushi Ikeda, François Guéna

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper attempts to determine if an Artificial Intelligence system using deep convolutional neural network (ConvNet) will be able to "imagine" architecture. Imagining architecture by means of algorithms can be affiliated to the research field of generative architecture. ConvNet makes it possible to avoid that difficulty by automatically extracting and classifying these rules as features from large example data. Moreover, image-base rendering algorithms can manipulate those abstract rules encoded in the ConvNet. From these rules and without constructing a prior 3D model, these algorithms can generate perspective of an architectural image. To conclude, establishing shape grammar with this automated system opens prospects for generative architecture with image-base rendering algorithms.

Original languageEnglish
Title of host publicationCAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias
Subtitle of host publicationTowards Continuous Designing
EditorsMarc Aurel Schnabel, Walaiporn Nakapan, Stanislav Roudavski, Sheng-Fen Chien, Mi Jeong Kim, Seungyeon Choo
PublisherThe Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)
Pages881-890
Number of pages10
ISBN (Electronic)9789881902672
Publication statusPublished - 2016 Jan 1
Event21st International Conference on Computer-Aided Architectural Design Research in Asia: Living Systems and Micro-Utopias: Towards Continuous Designing, CAADRIA 2016 - Melbourne, Australia
Duration: 2016 Mar 302016 Apr 2

Publication series

NameCAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing

Other

Other21st International Conference on Computer-Aided Architectural Design Research in Asia: Living Systems and Micro-Utopias: Towards Continuous Designing, CAADRIA 2016
CountryAustralia
CityMelbourne
Period16/3/3016/4/2

Keywords

  • Convolutional neural network
  • Generative design
  • Image-based rendering
  • Machine learning

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Building and Construction

Fingerprint Dive into the research topics of 'Artificial imagination of architecture with deep convolutional neural network "Laissez-faire": Loss of control in the esquisse phase'. Together they form a unique fingerprint.

  • Cite this

    Silvestre, J., Ikeda, Y., & Guéna, F. (2016). Artificial imagination of architecture with deep convolutional neural network "Laissez-faire": Loss of control in the esquisse phase. In M. A. Schnabel, W. Nakapan, S. Roudavski, S-F. Chien, M. J. Kim, & S. Choo (Eds.), CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing (pp. 881-890). (CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing). The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA).