Vision Without Surveillance
A scalable, privacy-preserving vision-language model (VLM) pipeline is developed that leverages zero-shot CLIP to extract 150+ interpretable urban design features from street-level imagery and enables scalable, evidence-based urban planning across cities.
Malikka Rajshahi, M. Alfonzo, Corey Ashby et al.
· Street Art & Urban Creat... · 0 citations