RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
Not on the map. Why?
Abstract (arXiv)
Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In this work, instead of pinhole and satellite images, we study robust MCVGL using holistic panoramas and OpenStreetMap (OSM). To this end, we establish a large-scale MCVGL benchmark dataset, CV-RHO, with over 2.7M images under different weather and lighting conditions, as well as sensor noise. Furthermore, we propose a model termed RHO with a two-branch Pin-Pan architecture for accurate visual localization. A Split-Undistort-Merge (SUM) module is introduced to address the panoramic distortion, and a Position-Orientation Fusion (POF) mechanism is designed to enhance the localization accuracy. Extensive experiments prove the value of our CV-RHO dataset and the effectiveness of the RHO model, with a significant performance gain up to 20% compared with the state-of-the-art baselines. Project page: https://github.com/InSAI-Lab/RHO.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 49 of its 72 references that are in the map. First posted on arXiv 29 Mar 2026.
Builds on
49 of 72 references.
References · 49
- 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
- 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 189
- 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 186
- 2019Lending Orientation to Neural Networks for Cross-view Geo-localizationcited by 180
- 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 168
- 2020University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localizationcited by 157
- 2023Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisationcited by 110
- 2019Optimal Feature Transport for Cross-View Image Geo-Localizationcited by 91
- 2022Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Imagecited by 88
- 2023OrienterNet: Visual Localization in 2D Public Maps with Neural Matchingcited by 84
- 2022Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondencecited by 70
- 2023Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimatorcited by 57
37 more
- 2022Uncertainty-aware Vision-based Metric Cross-view Geolocalizationcited by 54
- 2023Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformercited by 45
- 2024Cross-view image geo-localization with Panorama-BEV Co-Retrieval Networkcited by 40
- 2024Where am I? Cross-View Geo-localization with Natural Language Descriptionscited by 38
- 2020Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimationcited by 36
- 2023Convolutional Cross-View Pose Estimationcited by 36
- 2022Cross-View Image Sequence Geo-localizationcited by 31
- 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
- 2023GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglementcited by 28
- 2024ConGeo: Robust Cross-view Geo-localization across Ground View Variationscited by 27
- 2025FG2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matchingcited by 27
- 2022GAMa: Cross-view Video Geo-localizationcited by 23
- 2022Satellite Image Based Cross-view Localization for Autonomous Vehiclecited by 19
- 2024MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Mapscited by 18
- 2024Open Panoramic Segmentationcited by 17
- 2022Geo-Localization via Ground-to-Satellite Cross-View Image Retrievalcited by 16
- 2023View Consistent Purification for Accurate Cross-View Localizationcited by 15
- 2023Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materialscited by 14
- 2024Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truthcited by 14
- 2023U-BEV: Height-aware Bird's-Eye-View Segmentation and Neural Map-based Relocalizationcited by 13
- 2024Statewide Visual Geolocalization in the Wildcited by 12
- 2024Multi-weather Cross-view Geo-localization Using Denoising Diffusion Modelscited by 11
- 2024GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformerscited by 10
- 2023BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisationcited by 9
- 2025VAGeo: View-specific Attention for Cross-View Object Geo-Localizationcited by 9
- 2025BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localizationcited by 8
- 2025Scene-agnostic Pose Regression for Visual Localizationcited by 8
- 2025GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localizationcited by 8
- 2025Loc2: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matchingcited by 8
- 2024Deformable Mamba for Wide Field of View Segmentationcited by 7
- 2025SegLocNet: Multimodal Localization Network for Autonomous Driving via Bird's-Eye-View Segmentationcited by 6
- 2024OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Fused Geometric and Semantic Guidancecited by 5
- 2024BEVLoc: Cross-View Localization and Matching via Birds-Eye-View Synthesiscited by 4
- 2026More than the Sum: Panorama-Language Models for Adverse Omni-Scenescited by 4
- 2025DiffVL: Diffusion-Based Visual Localization on 2D Maps via BEV-Conditioned GPS Denoisingcited by 2
- 2026What if? Emulative Simulation with World Models for Situated Reasoningcited by 2
- 2025GLEAM: Learning to Match and Explain in Cross-View Geo-Localizationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.