Artificial Imagination of Architecture with Deep Convolutional Neural Network

This paper attempts to determine if an Artificial Intelli- gence 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 archi- tecture. ConvNet makes it possible to avoid that difficulty by automat- ically extracting and classifying these rules as features from large ex- ample data. Moreover, image-base rendering algorithms can manipu- late 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.