mlsanityData to 7 Oct 2026

Deep Learning the City : Quantifying Urban Perception At A Global Scale

arXiv 1608.01769 ↗First posted 5 Aug 2016cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

Computer vision methods that quantify the perception of urban environment are increasingly being used to study the relationship between a city's physical appearance and the behavior and health of its residents. Yet, the throughput of current methods is too limited to quantify the perception of cities across the world. To tackle this challenge, we introduce a new crowdsourced dataset containing 110,988 images from 56 cities, and 1,170,000 pairwise comparisons provided by 81,630 online volunteers along six perceptual attributes: safe, lively, boring, wealthy, depressing, and beautiful. Using this data, we train a Siamese-like convolutional neural architecture, which learns from a joint classification and ranking loss, to predict human judgments of pairwise image comparisons. Our results show that crowdsourcing combined with neural networks can produce urban perception data at the global scale.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 10; 2024: 10; 2025: 16; 2026: 20.

65 papers.

Sort:

By area:

  1. 2021Assessing bikeability with street view imagery and computer visioncited by 14
  2. 2023Learning to Compare Longitudinal Imagescited by 12
  3. 2025Global urban visual perception varies across demographics and personalitiescited by 10
  4. 2024A citizen science toolkit to collect human perceptions of urban environments using open street view imagescited by 9
  5. 2023Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?cited by 8
  6. 2024Urban Safety Perception Assessments via Integrating Multimodal Large Language Models with Street View Imagescited by 7
  7. 2025EMPLACE: Self-Supervised Urban Scene Change Detectioncited by 7
  8. 2025UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspectivecited by 7
  9. 2023Generative agents in the streets: Exploring the use of Large Language Models (LLMs) in collecting urban perceptionscited by 6
  10. 2022Geo-Information Harvesting from Social Media Datacited by 5
  11. 2025MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layoutscited by 5
  12. 2023UPDExplainer: an Interpretable Transformer-based Framework for Urban Physical Disorder Detection Using Street View Imagerycited by 4
38 more
  1. 2025Do Vision-Language Models See Urban Scenes as People Do? An Urban Perception Benchmarkcited by 4
  2. 2021Risk Prediction on Traffic Accidents using a Compact Neural Model for Multimodal Information Fusion over Urban Big Datacited by 3
  3. 2022Computer vision-based analysis of buildings and built environments: A systematic review of current approachescited by 3
  4. 2024URSimulator: Human-Perception-Driven Prompt Tuning for Enhanced Virtual Urban Renewal via Diffusion Modelscited by 3
  5. 2024ZenSVI: An Open-Source Software for the Integrated Acquisition, Processing and Analysis of Street View Imagery Towards Scalable Urban Sciencecited by 3
  6. 2025Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivitycited by 3
  7. 2025Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligencecited by 3
  8. 2023Computer vision-enriched discrete choice models, with an application to residential location choicecited by 2
  9. 2024From Efficiency to Equity: Measuring Fairness in Preference Learningcited by 2
  10. 2021On the Sample Complexity of Rank Regression from Pairwise Comparisonscited by 1
  11. 2022City-Wide Perceptions of Neighbourhood Quality using Street View Imagescited by 1
  12. 2023AutoLTS: Automating Cycling Stress Assessment via Contrastive Learning and Spatial Post-processingcited by 1
  13. 2023Climate-sensitive Urban Planning through Optimization of Tree Placementscited by 1
  14. 2024Artificial Intelligence in Landscape Architecture: A Surveycited by 1
  15. 2024AI-EDI-SPACE: A Co-designed Dataset for Evaluating the Quality of Public Spacescited by 1
  16. 2025Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Imagescited by 1
  17. 2025Artifacts of Idiosyncracy in Global Street View Datacited by 1
  18. 2025Urban Comfort Assessment in the Era of Digital Planning: A Multidimensional, Data-driven, and AI-assisted Frameworkcited by 1
  19. 2025How Well Do Vision--Language Models Understand Cities? A Comparative Study on Spatial Reasoning from Street-View Imagescited by 1
  20. 2025From Pixels to Predicates Structuring urban perception with scene graphscited by 1
  21. 2025Thinking on Maps: How Foundation Model Agents Explore, Remember, and Reason Map Environmentscited by 1
  22. 2026UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignmentcited by 1
  23. 2026Culturally uneven urban perception in large language modelscited by 1
  24. 2026Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiatedcited by 1
  25. 2022Predicting the impact of urban change in pedestrian and road safetycited by 0
  26. 2022Explainability of Deep Learning models for Urban Space perceptioncited by 0
  27. 2022Evaluating the Perceived Safety of Urban City via Maximum Entropy Deep Inverse Reinforcement Learningcited by 0
  28. 2023Urban Visual Intelligence: Studying Cities with AI and Street-level Imagerycited by 0
  29. 2023Scoring Cycling Environments Perceived Safety using Pairwise Image Comparisonscited by 0
  30. 2023Explainable Severity ranking via pairwise n-hidden comparison: a case study of glaucomacited by 0
  31. 2024Cross-Modal Learning of Housing Quality in Amsterdamcited by 0
  32. 2024Congestion Forecast for Trains with Railroad-Graph-based Semi-Supervised Learning using Sparse Passenger Reportscited by 0
  33. 2024A utility-based spatial analysis of residential street-level conditions; A case study of Rotterdamcited by 0
  34. 2025Learning Street View Representations with Spatiotemporal Contrastcited by 0
  35. 2025Do Streetscapes Still Matter for Customer Ratings of Eating and Drinking Establishments in Car-Dependent Cities?cited by 0
  36. 2025From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural Chinacited by 0
  37. 2026Virtual Urbanism: An AI-Driven Framework for Quantifying Urban Identity. A Tokyo-Based Pilot Study Using Diffusion-Generated Synthetic Environmentscited by 0
  38. 2026How Many Visual Levers Drive Urban Perception? Interventional Counterfactuals via Multiple Localised Editscited by 0

50 most cited of 65 All 65 (JSON)