Human–AI Alignment in Architectural and Streetscape Evaluation: A Multi-City Study Using Vision–Language Models and Explainable Street-View Analysis
Buildings · 16.11.2026 · 16 (22) · 4568
DOI: 10.3390/buildings16224568 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 16.11.2026. Verfasst von Yuanyuan Mou und 1 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
AI systems may agree with one another about the quality of buildings and streets, even when their judgments differ from people’s. We tested this possibility using 120 paired building-frontage and streetscape images selected from 39,047 street-view panoramas across six Chinese urban districts. The images were rated by 100 architecture or urban-planning students, 100 students from other disciplines, and five vision–language models (VLMs). The two student groups strongly agreed on how they ranked the images (Spearman correlations of 0.914–0.946 for building frontages and 0.923–0.943 for streetscapes), although architecture/planning students consistently gave lower scores. By contrast, the AI models agreed relatively well with one another but showed little correspondence with either student group in their rankings. We also examined whether visible elements such as vegetation, roads, sidewalks, and sky could explain the ratings. These simple image features predicted AI streetscape scores more successfully than human scores, consistent with the possibility that their evaluations reflect different visual cues, although the study could not establish how either reached its judgments. AI may support preliminary screening of large image collections, but human evaluation remains essential for architectural and urban-design decisions.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Mou, Y., & Li, X. (2026). Human–AI Alignment in Architectural and Streetscape Evaluation: A Multi-City Study Using Vision–Language Models and Explainable Street-View Analysis. Buildings, 16(22), 4568. https://doi.org/10.3390/buildings16224568
Vancouver
Mou Y, Li X. Human–AI Alignment in Architectural and Streetscape Evaluation: A Multi-City Study Using Vision–Language Models and Explainable Street-View Analysis. Buildings. 2026;16(22):4568. doi:10.3390/buildings16224568
BibTeX
@article{Mou2026,
author = {Mou, Yuanyuan and Li, Xin},
title = {Human–AI Alignment in Architectural and Streetscape Evaluation: A Multi-City Study Using Vision–Language Models and Explainable Street-View Analysis},
journal = {Buildings},
year = {2026},
volume = {16},
number = {22},
pages = {4568},
doi = {10.3390/buildings16224568}
}
EUVIMED