aiqbench analysis
This study demonstrates how large vision-language models can automate the assessment of urban blight by analyzing multiple street views for structural defects like roof damage and broken windows. By combining ensemble learning techniques with XGBoost, the framework achieves robust performance that rivals professional human surveys while significantly reducing labor costs. This approach offers a scalable solution for city planners to monitor housing stock conditions in real-time without relying on expensive traditional inspection cycles.
Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit
arXiv:2608.01753v1 Announce Type: cross Abstract: Addressing urban blight has seen increased focus in the past 15 years. Assessing urban blight is essential for guiding urban planning, targeting rehabilitation, and safeguarding public health, yet traditional residential blight surveys are difficult to maintain at scale due to the labor-intensive cost and long-term cycle. This study introduced a scalable framework for estimating residential blight using open-source large vision-language models on multiple views. Structured prompts guided models to evaluate housing attributes, including roof integrity, wall damage, and broken or boarded openings, producing both binary assessments and probabilistic estimates of disrepair. To evaluate the performance of these visual assessments, we compared professional human annotations of these features across several models, including an ensemble stacking approach based on XGBoost and a weighted scoring system. Results showed that (i) multiple street views can contribute to the improvement of accuracy, (ii) large vision-language models have different strengths of inference, (iii) the ensemble learner outperforms individual base models, enhancing robustness across all residential conditions and blight assessment. The practical application of the method allows low-cost tracking and management of housing stock conditions, providing a regularly updatable complement to traditional blight surveys.
Abstract:Addressing urban blight has seen increased focus in the past 15 years. Assessing urban blight is essential for guiding urban planning, targeting rehabilitation, and safeguarding public health, yet traditional residential blight surveys are difficult to maintain at scale due to the labor-intensive cost and long-term cycle. This study introduced a scalable framework for estimating residential blight using open-source large vision-language models on multiple views. Structured prompts guided models to evaluate housing attributes, including roof integrity, wall damage, and broken or boarded openings, producing both binary assessments and probabilistic estimates of disrepair. To evaluate the performance of these visual assessments, we compared professional human annotations of these features across several models, including an ensemble stacking approach based on XGBoost and a weighted scoring system. Results showed that (i) multiple street views can contribute to the improvement of accuracy, (ii) large vision-language models have different strengths of inference, (iii) the ensemble learner outperforms individual base models, enhancing robustness across all residential conditions and blight assessment. The practical application of the method allows low-cost tracking and management of housing stock conditions, providing a regularly updatable complement to traditional blight surveys.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2608.01753 [cs.CV]
(or arXiv:2608.01753v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.01753 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 287 words
Related coverage
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026
NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry
NVIDIA · Jul 15, 2026
Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery?
arXiv · Sep 17, 2026
Knowledge-Guided Vision-Language Inference for Image-Based Urban Flood Depth Estimation
arXiv · Sep 9, 2026