From Clay to Code: Typological and Material Reasoning in AI Interpretations of Iranian Pigeon Towers

TL;DR

This paper examines how generative AI models interpret Iranian pigeon towers, revealing strengths in geometric reproduction but limitations in material and cultural understanding, thus highlighting boundaries in AI's architectural reasoning.

Contribution

It introduces a framework for evaluating AI's interpretation of vernacular architecture, focusing on typology, materiality, and cultural specificity, using Iranian pigeon towers as a case study.

Findings

AI reliably reproduces geometric patterns

AI misreads material and climatic reasoning

Reference imagery enhances realism but reduces creativity

Abstract

This study investigates how generative AI systems interpret the architectural intelligence embedded in vernacular form. Using the Iranian pigeon tower as a case study, the research tests three diffusion models, Midjourney v6, DALL-E 3, and DreamStudio based on Stable Diffusion XL (SDXL), across three prompt stages: referential, adaptive, and speculative. A five-criteria evaluation framework assesses how each system reconstructs typology, materiality, environment, realism, and cultural specificity. Results show that AI reliably reproduces geometric patterns but misreads material and climatic reasoning. Reference imagery improves realism yet limits creativity, while freedom from reference generates inventive but culturally ambiguous outcomes. The findings define a boundary between visual resemblance and architectural reasoning, positioning computational vernacular reasoning as a framework for analyzing how AI perceives, distorts, and reimagines traditional design intelligence.