Data to 14 Oct 2026

From Coarse to Fine: Robust Hierarchical Localization at Large Scale

arXiv 1812.03506 ↗First posted 9 Dec 2018cs.CVcited by 559

Not on the map. Why?

Abstract (arXiv)

Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augmented reality. It remains, however, a challenging task, particularly for large-scale environments and in presence of significant appearance changes. State-of-the-art methods not only struggle with such scenarios, but are often too resource intensive for certain real-time applications. In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization. We exploit the coarse-to-fine localization paradigm: we first perform a global retrieval to obtain location hypotheses and only later match local features within those candidate places. This hierarchical approach incurs significant runtime savings and makes our system suitable for real-time operation. By leveraging learned descriptors, our method achieves remarkable localization robustness across large variations of appearance and sets a new state-of-the-art on two challenging benchmarks for large-scale localization.

Key facts. Cited by 559 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 57; 2022: 77; 2023: 101; 2024: 121; 2025: 122; 2026: 81.

559 papers.

Sort:

By area:

2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
2024Grounding Image Matching in 3D with MASt3Rcited by 983
2023LightGlue: Local Feature Matching at Light Speedcited by 590
2023RoMa: Robust Dense Feature Matchingcited by 302
2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171

38 more

2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 161
2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
2023Optimal Transport Aggregation for Visual Place Recognitioncited by 152
2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 120
2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 100
2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
2023OrienterNet: Visual Localization in 2D Public Maps with Neural Matchingcited by 84
2021Where is your place, Visual Place Recognition?cited by 82
2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
2024Local All-Pair Correspondence for Point Trackingcited by 80
2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 78
2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72
2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 66
2021On the Limits of Pseudo Ground Truth in Visual Camera Re-localisationcited by 63
2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
2022MeshLoc: Mesh-Based Visual Localizationcited by 62
2022DeepLSD: Line Segment Detection and Refinement with Deep Image Gradientscited by 60
2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
2025MegaLoc: One Retrieval to Place Them Allcited by 60
2021SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognitioncited by 57
2021DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurescited by 54
2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53

50 most cited of 559 All 559 (JSON)