Machine Apophenia: The Kaleidoscopic Generation of Architectural Images

TL;DR

This paper introduces a novel AI-based method called machine apophenia that combines neural networks to generate unique architectural images, demonstrating improvements in aesthetic quality through iterative refinement and social media sharing.

Contribution

It presents a new methodology for generating architectural images using multiple neural networks and the concept of machine apophenia, emphasizing unsupervised, creative image synthesis.

Findings

Improved aesthetic and technical metrics of generated images

Effective iterative refinement process

Successful social media sharing of generated images

Abstract

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.