Multi-agent system suggests city design changes to improve urban views
From Pixels to Policy: A Multi-Agent System for Intervention and Geo-Spatial Decision Support
Computer Vision and Pattern Recognition
Summary
Changing how cities look can affect how safe and pleasant they feel, but it's hard and expensive to test ideas before building them. The authors created a computer system called VIDA-Geo that uses pictures from above and street level to suggest changes—like adding trees or fixing sidewalks—that could make a neighborhood look safer or greener. Their system tries out these changes digitally to see if they really help, giving city planners several good options to consider. This makes it easier to plan better cities without costly experiments on the ground.
What this means in practice
- •For city planners: Provide multiple realistic intervention options in urban design with predicted impacts on safety and greenery based on local imagery.
- •For environmental consultants: Generate and evaluate visual proposals for environmental improvements in urban spaces using aerial and street-level photos.
Authors
Hosam Elgendy, Utkarsh Mall
Abstract
Urban environments are shaped by design choices with long-term implications for health, safety, and quality of life, yet evaluating proposed interventions remains costly, time-consuming, and often impractical. Existing geospatial vision methods largely focus on monitoring urban indicators from aerial and street-view imagery, rather than proposing interventions and estimating their effects on such indicators. Moving beyond recognition, we introduce the problem of discovering interventions that improve target indicators for a given aerial or street-view image. We argue that a black-box indicator model, combined with a generative editing model, can serve as an implicit digital twin for testing intervention hypotheses. We present VIDA-Geo , a multi-agent system that explores this intervention space by coordinating segmentation, diffusion-based inpainting, and indicator scoring models to produce interventions that are both perceptually realistic and aligned with real-world policies. We evaluate our system on 8 indicators across aerial and street-view imagery, measuring changes in factors such as perceived safety and greenery. Our approach outperforms existing baselines in many cases, achieving up to 2X higher perceptual quality and policy alignment scores. Finally, our model provides users with multiple candidate interventions, supporting an expert city-planner-in-the-loop workflow.