mlsanityData to 14 Oct 2026

TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization

arXiv 2204.00097 ↗First posted 31 Mar 2022cs.CVcited by 168

Not on the map. Why?

Abstract (arXiv)

The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. We propose a pure transformer-based approach (TransGeo) to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of transformer related to global information modeling and explicit position information encoding. We further leverage the flexibility of transformer input and propose an attention-guided non-uniform cropping method, so that uninformative image patches are removed with negligible drop on performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This "attend and zoom-in" strategy is highly similar to human behavior when observing images. Remarkably, TransGeo achieves state-of-the-art results on both urban and rural datasets, with significantly less computation cost than CNN-based methods. It does not rely on polar transform and infers faster than CNN-based methods. Code is available at https://github.com/Jeff-Zilence/TransGeo2022.

Key facts. Cited by 168 papers in the map (data through 14 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

26 of 37 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  10. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  11. 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
  12. 2021When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentationscited by 260
14 more
  1. 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 189
  2. 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 186
  3. 2019Lending Orientation to Neural Networks for Cross-view Geo-localizationcited by 180
  4. 2020Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matchingcited by 126
  5. 2021Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localizationcited by 113
  6. 2018Learning to Navigate in Cities Without a Mapcited by 104
  7. 2019Bridging the Domain Gap for Ground-to-Aerial Image Matchingcited by 95
  8. 2016Localizing and Orienting Street Views Using Overhead Imagerycited by 94
  9. 2016Predicting Ground-Level Scene Layout from Aerial Imagerycited by 90
  10. 2017Cross-View Image Matching for Geo-localization in Urban Environmentscited by 69
  11. 2020Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimationcited by 36
  12. 2019GeoCapsNet: Aerial to Ground view Image Geo-localization using Capsule Networkcited by 18
  13. 2019Cross-View Policy Learning for Street Navigationcited by 12
  14. 2019Accurate Visual Localization for Automotive Applicationscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 11; 2023: 22; 2024: 38; 2025: 38; 2026: 59.

168 papers.

Sort:

By area:

  1. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 187
  2. 2023Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisationcited by 110
  3. 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
  4. 2022Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondencecited by 70
  5. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  6. 2023Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimatorcited by 57
  7. 2023PIGEON: Predicting Image Geolocationscited by 56
  8. 2023Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenescited by 55
  9. 2022Uncertainty-aware Vision-based Metric Cross-view Geolocalizationcited by 54
  10. 2022Visual Cross-View Metric Localization with Dense Uncertainty Estimatescited by 48
  11. 2022SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimationcited by 46
  12. 2023Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformercited by 45
38 more
  1. 2023Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matchingcited by 42
  2. 2024Cross-view image geo-localization with Panorama-BEV Co-Retrieval Networkcited by 40
  3. 2022Deep Learning for Omnidirectional Vision: A Survey and New Perspectivescited by 38
  4. 2023Simple, Effective and General: A New Backbone for Cross-view Image Geo-localizationcited by 37
  5. 2023Convolutional Cross-View Pose Estimationcited by 36
  6. 2024G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Modelscited by 34
  7. 2024Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generationcited by 32
  8. 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
  9. 2023GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglementcited by 28
  10. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Modelscited by 28
  11. 2024ConGeo: Robust Cross-view Geo-localization across Ground View Variationscited by 27
  12. 2024GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Modelcited by 27
  13. 2022CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localizationcited by 25
  14. 2024Game4Loc: A UAV Geo-Localization Benchmark from Game Datacited by 24
  15. 2025Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Frameworkcited by 24
  16. 2024Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IANcited by 23
  17. 2024CV-Cities: Advancing Cross-View Geo-Localization in Global Citiescited by 22
  18. 2025GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalizationcited by 19
  19. 2024SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentationcited by 18
  20. 2022Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularizationcited by 17
  21. 2024Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localizationcited by 17
  22. 2024Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localizationcited by 16
  23. 2024Cross-view geo-localization: a surveycited by 15
  24. 2024Weakly-supervised Camera Localization by Ground-to-satellite Image Registrationcited by 15
  25. 2023Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspectivecited by 14
  26. 2023Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materialscited by 14
  27. 2024Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truthcited by 14
  28. 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chainscited by 14
  29. 2024Statewide Visual Geolocalization in the Wildcited by 12
  30. 2025From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Modelscited by 12
  31. 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localizationcited by 11
  32. 2024Towards Interactive Global Geolocation Assistantcited by 11
  33. 2025GT-Loc: Unifying When and Where in Images Through a Joint Embedding Spacecited by 11
  34. 2023Cross-View Visual Geo-Localization for Outdoor Augmented Realitycited by 10
  35. 2023CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognitioncited by 10
  36. 2023C-BEV: Contrastive Bird's Eye View Training for Cross-View Image Retrieval and 3-DoF Pose Estimationcited by 10
  37. 2024GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformerscited by 10
  38. 2024CityGuessr: City-Level Video Geo-Localization on a Global Scalecited by 10

50 most cited of 168 All 168 (JSON)