# FG2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching

arXiv: https://arxiv.org/abs/2503.18725 · HTML: https://mlsanity.com/paper/2503.18725/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 53 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC](https://mlsanity.com/paper/2002.12324/) (2020)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image](https://mlsanity.com/paper/2204.04752/) (2022)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator](https://mlsanity.com/paper/2308.16906/) (2023)
- [Uncertainty-aware Vision-based Metric Cross-view Geolocalization](https://mlsanity.com/paper/2211.12145/) (2022)
- [Visual Cross-View Metric Localization with Dense Uncertainty Estimates](https://mlsanity.com/paper/2208.08519/) (2022)
- [SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation](https://mlsanity.com/paper/2211.14651/) (2022)
- [Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer](https://mlsanity.com/paper/2307.08015/) (2023)
- [Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching](https://mlsanity.com/paper/2203.14148/) (2022)
- [End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans](https://mlsanity.com/paper/1906.04201/) (2019)
- [SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding](https://mlsanity.com/paper/2306.05407/) (2023)
- [Convolutional Cross-View Pose Estimation](https://mlsanity.com/paper/2303.05915/) (2023)
- [LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments](https://mlsanity.com/paper/2104.09169/) (2021)
- [UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities](https://mlsanity.com/paper/2309.14516/) (2023)
- [ConGeo: Robust Cross-view Geo-localization across Ground View Variations](https://mlsanity.com/paper/2403.13965/) (2024)
- [Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences](https://mlsanity.com/paper/2404.06337/) (2024)
- [LASER: LAtent SpacE Rendering for 2D Visual Localization](https://mlsanity.com/paper/2204.00157/) (2022)

## Built on by (most cited first, 27 of 27)

- [Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models](https://mlsanity.com/paper/2506.14674/) (2025)
- [Seeing through Satellite Images at Street Views](https://mlsanity.com/paper/2505.17001/) (2025)
- [Loc2: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching](https://mlsanity.com/paper/2509.09792/) (2025)
- [Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach](https://mlsanity.com/paper/2601.00388/) (2026)
- [GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration](https://mlsanity.com/paper/2508.00152/) (2025)
- [ViewBridge:Revisiting Cross-View Localization from Image Matching](https://mlsanity.com/paper/2508.10716/) (2025)
- [MOGeo: Beyond One-to-One Cross-View Object Geo-localization](https://mlsanity.com/paper/2603.13843/) (2026)
- [Interpretable Perception and Reasoning for Audiovisual Geolocation](https://mlsanity.com/paper/2603.05708/) (2026)
- [Just Zoom In: Cross-View Geo-Localization via Autoregressive Zooming](https://mlsanity.com/paper/2603.25686/) (2026)
- [RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization](https://mlsanity.com/paper/2603.27758/) (2026)
- [SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes](https://mlsanity.com/paper/2608.07835/) (2026)
- [VIRD: View-Invariant Representation through Dual-Axis Transformation for Cross-View Pose Estimation](https://mlsanity.com/paper/2603.12918/) (2026)
- [GeoFlow: Real-Time Fine-Grained Cross-View Geolocalization via Iterative Flow Prediction](https://mlsanity.com/paper/2603.21943/) (2026)
- [TACO: Trajectory Aligning Cross-view Optimisation](https://mlsanity.com/paper/2605.03315/) (2026)
- [Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images](https://mlsanity.com/paper/2605.07978/) (2026)
- [Empowering Feed-Forward Reconstruction Models with Metric Scale via Satellite Images](https://mlsanity.com/paper/2606.08205/) (2026)
- [Fusing Satellite Imagery and Planimetric Maps for Cross-View Localization](https://mlsanity.com/paper/2606.10166/) (2026)
- [Globally Localizing Lunar Rover in Pixels via Graph Alignment](https://mlsanity.com/paper/2606.10602/) (2026)
- [Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring](https://mlsanity.com/paper/2606.22094/) (2026)
- [More Than Where You Are: Learning Semantics, Structure, and Geometry from Cross-View Localization](https://mlsanity.com/paper/2607.12429/) (2026)
- [Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving](https://mlsanity.com/paper/2608.10660/) (2026)
- [OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization](https://mlsanity.com/paper/2608.25274/) (2026)
- [Pixel-wise Geo-registration of Drone and Satellite Images](https://mlsanity.com/paper/2608.28891/) (2026)
- [Ground-to-Satellite Localization in Unconstrained Image Collections for 3D Scene Reconstruction](https://mlsanity.com/paper/2608.29211/) (2026)
- [AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels](https://mlsanity.com/paper/2609.02798/) (2026)
- [ARC-Loc: Leveraging Azimuthal Ray Convergence as a Geometric Cue for Direct Cross-View Localization](https://mlsanity.com/paper/2609.04965/) (2026)
- [How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization](https://mlsanity.com/paper/2609.39127/) (2026)

## Abstract (arXiv)

We propose a novel fine-grained cross-view localization method that estimates the 3 Degrees of Freedom pose of a ground-level image in an aerial image of the surroundings by matching fine-grained features between the two images. The pose is estimated by aligning a point plane generated from the ground image with a point plane sampled from the aerial image. To generate the ground points, we first map ground image features to a 3D point cloud. Our method then learns to select features along the height dimension to pool the 3D points to a Bird's-Eye-View (BEV) plane. This selection enables us to trace which feature in the ground image contributes to the BEV representation. Next, we sample a set of sparse matches from computed point correspondences between the two point planes and compute their relative pose using Procrustes alignment. Compared to the previous state-of-the-art, our method reduces the mean localization error by 28% on the VIGOR cross-area test set. Qualitative results show that our method learns semantically consistent matches across ground and aerial views through weakly supervised learning from the camera pose.