mlsanityData to 7 Oct 2026

OpenStreetView-5M: The Many Roads to Global Visual Geolocation

arXiv 2404.18873 ↗First posted 29 Apr 2024cs.CV cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of learned geographical features beyond mere memorization. To demonstrate the utility of our dataset, we conduct an extensive benchmark of various state-of-the-art image encoders, spatial representations, and training strategies. All associated codes and models can be found at https://github.com/gastruc/osv5m.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 35 of its 85 references that are in the map. First posted on arXiv 29 Apr 2024.

Builds on

35 of 85 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2017Billion-scale similarity search with GPUscited by 2,477
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2018Group Normalizationcited by 1,514
  12. 2018Datasheets for Datasetscited by 1,371
23 more
  1. 2021Robust fine-tuning of zero-shot modelscited by 785
  2. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  3. 2021ImageNet-21K Pretraining for the Massescited by 607
  4. 2019End-to-End Learning of Visual Representations from Uncurated Instructional Videoscited by 506
  5. 2023Demystifying CLIP Datacited by 265
  6. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 236
  7. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  8. 2016PlaNet - Photo Geolocation with Convolutional Neural Networkscited by 114
  9. 2019Presence-Only Geographical Priors for Fine-Grained Image Classificationcited by 109
  10. 2017Revisiting IM2GPS in the Deep Learning Eracited by 79
  11. 2018CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Mapscited by 68
  12. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  13. 2023Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenescited by 55
  14. 2023PIGEON: Predicting Image Geolocationscited by 55
  15. 2019The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scalecited by 49
  16. 2019The StreetLearn Environment and Datasetcited by 42
  17. 2020Benchmarking Image Retrieval for Visual Localizationcited by 42
  18. 2023Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalizationcited by 41
  19. 2021Interpretable Semantic Photo Geolocationcited by 32
  20. 2021Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimationcited by 19
  21. 2021CrowdDriven: A New Challenging Dataset for Outdoor Visual Localizationcited by 13
  22. 2022G^3: Geolocation via Guidebook Groundingcited by 12
  23. 2018Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 18; 2026: 17.

38 papers.

Sort:

By area:

  1. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Modelscited by 27
  2. 2024Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocationcited by 23
  3. 2025Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Frameworkcited by 23
  4. 2025UniVG: A Generalist Diffusion Model for Unified Image Generation and Editingcited by 19
  5. 2025GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalizationcited by 18
  6. 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chainscited by 14
  7. 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localizationcited by 11
  8. 2024Towards Interactive Global Geolocation Assistantcited by 11
  9. 2025GT-Loc: Unifying When and Where in Images Through a Joint Embedding Spacecited by 11
  10. 2025Scaling Image Geo-Localization to Continent Levelcited by 10
  11. 2025GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Modelscited by 9
  12. 2025Culture in Action: Evaluating Text-to-Image Models through Social Activitiescited by 9
26 more
  1. 2025NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localizationcited by 8
  2. 2025LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Spacecited by 6
  3. 2025Towards Generative Location Awareness for Disaster Response: A Probabilistic Cross-view Geolocalization Approachcited by 6
  4. 2025GPS as a Control Signal for Image Generationcited by 5
  5. 2025GeoExplorer: Active Geo-localization with Curiosity-Driven Explorationcited by 3
  6. 2026Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoningcited by 3
  7. 2025GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddingscited by 2
  8. 2025Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Startcited by 2
  9. 2026TIGeR: A Unified Framework for Time, Images and Geo-location Retrievalcited by 2
  10. 2026REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localizationcited by 2
  11. 2025Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generationcited by 1
  12. 2026Interpretable Perception and Reasoning for Audiovisual Geolocationcited by 1
  13. 2026UNIGEOCLIP: Unified Geospatial Contrastive Learningcited by 1
  14. 2026VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scalecited by 1
  15. 2025MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understandingcited by 0
  16. 2026LocationAgent: A Hierarchical Agent for Image Geolocation via Decoupling Strategy and Evidence from Parametric Knowledgecited by 0
  17. 2026Where Do Images Come From? Analyzing Captions to Geographically Profile Datasetscited by 0
  18. 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generationcited by 0
  19. 2026GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalizationcited by 0
  20. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalizationcited by 0
  21. 2026Object-Level Explanations for Image Geolocation Models: a GeoGuessr use-casecited by 0
  22. 2026Pinpoint: Grounded Worldwide Image Geolocation via Cross-Source Retrieval and Rerankingcited by 0
  23. 2026GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity in Text-to-Image Street-View Generationcited by 0
  24. 2026Defending from GeoLocalization through Adversarial Road Tripscited by 0
  25. 2026GeoBridge: Decoupled Semantic Conditioning for Generative Image Geolocalizationcited by 0
  26. 2026What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptationcited by 0