TY - GEN
T1 - Artificial imagination of architecture with deep convolutional neural network "Laissez-faire"
T2 - 21st International Conference on Computer-Aided Architectural Design Research in Asia: Living Systems and Micro-Utopias: Towards Continuous Designing, CAADRIA 2016
AU - Silvestre, Joaquim
AU - Ikeda, Yasushi
AU - Guéna, François
N1 - Publisher Copyright:
© 2016, The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA), Hong Kong.
PY - 2016
Y1 - 2016
N2 - 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.
AB - 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.
KW - Convolutional neural network
KW - Generative design
KW - Image-based rendering
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=84973534445&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973534445&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84973534445
T3 - CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias: Towards Continuous Designing
SP - 881
EP - 890
BT - CAADRIA 2016, 21st International Conference on Computer-Aided Architectural Design Research in Asia - Living Systems and Micro-Utopias
A2 - Schnabel, Marc Aurel
A2 - Nakapan, Walaiporn
A2 - Roudavski, Stanislav
A2 - Chien, Sheng-Fen
A2 - Kim, Mi Jeong
A2 - Choo, Seungyeon
PB - The Association for Computer-Aided Architectural Design Research in Asia (CAADRIA)
Y2 - 30 March 2016 through 2 April 2016
ER -