Artificial Imagination of Architecture with Deep Convolutional Neural Network

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.

Generative systems in the architecture, engineering and construction industry: A systematic review and analysis

“…Besides, due to the prominence of AI and ML application in virtually every domain, we believe it would be useful for the reader to present some applications where researchers paired AI and ML techniques with generative techniques. In this context, Silvestre et al 127 argue that ML facilitates the incorporation of GSs in the architectural design process through extracting the algorithms that govern the generation process, and they proposed a system that couples convolutional neural network with SG to generate architectural designs. That is why Ruiz-Montiel et al 128 pair reinforced learning (RL), dynamic programming is particular, with SG to develop a GS dedicated to developing two-dimensional layouts for single-family houses.…”

Think AI-side the Box! Exploring the Usability of text-to-image generators for architecture students

“…Recent advances in generative machine learning models have demonstrated the potential to revolutionize the field of architecture by introducing a new kind of creative behavior enabled by Artificial Intelligence (AI) tools. For example, Generative Adversarial Networks (GAN) models have already been used in specific architectural tasks such as plan generation (Chaillou, 2020;Zheng et al, 2020), concept image generation (Silvestre et al, 2016;Eroğlu & Gül, 2022) and urban planning (Boim et al, 2022;Zhong et al, 2022). Recently, new image generation diffusion models have demonstrated an extraordinary capability to produce novel and creative architectural illustrations, including architectural designs from text descriptions and images (Ramesh et al, 2021).…”

Machine learning and complex compositional principles in architecture: Application of convolutional neural networks for generation of context-dependent spatial compositions

“…Among the holistic applications, Google Deep Dream 12 and neural style transfer 13 have been utilized to generate perspective views of architectural scenes. 14 AlexNet 5 and GoogLeNet 15 were applied in the extraction of ImageNet classes 16 from the spherical images captured in a 3D model of Osaka City. 17 Generative Adversarial CNNs 18 were used to generate new, Islamic, geometric patterns based on provided examples 19 and a CNN was trained to distinguish architectural plans from sections.…”