Machine Apophenia: The Kaleidoscopic Generation of Architectural Images
This work addresses architectural design automation, but it appears incremental as it builds on existing generative AI methods without a clear breakthrough.
The study tackled the problem of generating architectural images using generative AI by combining multiple neural networks in an unsupervised process, resulting in improved technical and aesthetic metrics at each step.
This study investigates the application of generative artificial intelligence in architectural design. We present a novel methodology that combines multiple neural networks to create an unsupervised and unmoderated stream of unique architectural images. Our approach is grounded in the conceptual framework called machine apophenia. We hypothesize that neural networks, trained on diverse human-generated data, internalize aesthetic preferences and tend to produce coherent designs even from random inputs. The methodology involves an iterative process of image generation, description, and refinement, resulting in captioned architectural postcards automatically shared on several social media platforms. Evaluation and ablation studies show the improvement both in technical and aesthetic metrics of resulting images on each step.