mlsanityData to 7 Oct 2026

Is Geometry Enough for Matching in Visual Localization?

arXiv 2203.12979 ↗First posted 24 Mar 2022cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose to go beyond the well-established approach to vision-based localization that relies on visual descriptor matching between a query image and a 3D point cloud. While matching keypoints via visual descriptors makes localization highly accurate, it has significant storage demands, raises privacy concerns and requires update to the descriptors in the long-term. To elegantly address those practical challenges for large-scale localization, we present GoMatch, an alternative to visual-based matching that solely relies on geometric information for matching image keypoints to maps, represented as sets of bearing vectors. Our novel bearing vectors representation of 3D points, significantly relieves the cross-modal challenge in geometric-based matching that prevented prior work to tackle localization in a realistic environment. With additional careful architecture design, GoMatch improves over prior geometric-based matching work with a reduction of (10.67m,95.7deg) and (1.43m, 34.7deg) in average median pose errors on Cambridge Landmarks and 7-Scenes, while requiring as little as 1.5/1.7% of storage capacity in comparison to the best visual-based matching methods. This confirms its potential and feasibility for real-world localization and opens the door to future efforts in advancing city-scale visual localization methods that do not require storing visual descriptors.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 53 of its 85 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

53 of 85 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  6. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  8. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  10. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
38 more
  1. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  2. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
  3. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  4. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  5. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  6. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  7. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  8. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  9. 2017Learning to Find Good Correspondencescited by 176
  10. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  11. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  12. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  13. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  14. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 133
  15. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  16. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 129
  17. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  18. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  19. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  20. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  21. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  22. 2019Revealing Scenes by Inverting Structure from Motion Reconstructionscited by 66
  23. 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
  24. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  25. 2017Semantic Visual Localizationcited by 54
  26. 2019Privacy Preserving Image-Based Localizationcited by 47
  27. 2018Hybrid Scene Compression for Visual Localizationcited by 40
  28. 2019Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Taskcited by 39
  29. 2020Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimizationcited by 38
  30. 2017An Efficient Algebraic Solution to the Perspective-Three-Point Problemcited by 29
  31. 2019Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisationcited by 28
  32. 2020S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matchingcited by 22
  33. 2021NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learningcited by 21
  34. 2018The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimationcited by 20
  35. 2021How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Linescited by 19
  36. 2019Cascaded Parallel Filtering for Memory-Efficient Image-Based Localizationcited by 17
  37. 2020Cross-Descriptor Visual Localization and Mappingcited by 15
  38. 2020Efficient Scene Compression for Visual-based Localizationcited by 12

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 10; 2024: 13; 2025: 14; 2026: 10.

48 papers.

Sort:

By area:

  1. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  2. 2023OrienterNet: Visual Localization in 2D Public Maps with Neural Matchingcited by 84
  3. 2024GLACE: Global Local Accelerated Coordinate Encodingcited by 48
  4. 2024Map-Relative Pose Regression for Visual Re-Localizationcited by 42
  5. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  6. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 35
  7. 2024The NeRFect Match: Exploring NeRF Features for Visual Localizationcited by 32
  8. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  9. 2023DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matchingcited by 17
  10. 2023FocusTune: Tuning Visual Localization through Focus-Guided Samplingcited by 16
  11. 2025R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localizationcited by 16
  12. 2026VGG-T3: Offline Feed-Forward 3D Reconstruction at Scalecited by 14
36 more
  1. 2024LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignmentcited by 12
  2. 2024Fully Geometric Panoramic Localizationcited by 11
  3. 2024Learning to Produce Semi-dense Correspondences for Visual Localizationcited by 10
  4. 2025Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localizationcited by 10
  5. 2023Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinementcited by 9
  6. 2024Differentiable Product Quantization for Memory Efficient Camera Relocalizationcited by 9
  7. 2025A Guide to Structureless Visual Localizationcited by 9
  8. 2025ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Trainingcited by 8
  9. 2023Privacy-Preserving Representations are not Enough -- Recovering Scene Content from Camera Posescited by 7
  10. 2022Privacy-Preserving Visual Localization with Event Camerascited by 6
  11. 2023Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Imagescited by 6
  12. 2024Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Informationcited by 6
  13. 2025GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representationscited by 5
  14. 2024Improved Scene Landmark Detection for Camera Localizationcited by 4
  15. 2023DAC: Detector-Agnostic Spatial Covariances for Deep Local Featurescited by 3
  16. 2025A2-GNN: Angle-Annular GNN for Visual Descriptor-free Camera Relocalizationcited by 3
  17. 2025EdgeRegNet: Edge Feature-based Multimodal Registration Network between Images and LiDAR Point Cloudscited by 3
  18. 2025Can we make NeRF-based visual localization privacy-preserving?cited by 3
  19. 2025ColabSfM: Collaborative Structure-from-Motion by Point Cloud Registrationcited by 2
  20. 2024STT: Stateful Tracking with Transformers for Autonomous Drivingcited by 1
  21. 2024EEPNet: Efficient Edge Pixel-based Matching Network for Cross-Modal Dynamic Registration between LiDAR and Cameracited by 1
  22. 2024Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Informationcited by 1
  23. 2026ImLoc: Revisiting Visual Localization with Image-based Representationcited by 1
  24. 2025Geometry-aided Vision-based Localization of Future Mars Helicopters in Challenging Illumination Conditionscited by 0
  25. 2025A-SCoRe: Attention-based Scene Coordinate Regression for wide-ranging scenarioscited by 0
  26. 2025EEPNet-V2: Patch-to-Pixel Solution for Efficient Cross-Modal Registration between LiDAR Point Cloud and Camera Imagecited by 0
  27. 2025MACE: Mixture-of-Experts Accelerated Coordinate Encoding for Large-Scale Scene Localization and Renderingcited by 0
  28. 2025Visible Structure Retrieval for Lightweight Image-Based Relocalisationcited by 0
  29. 2026PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matchingcited by 0
  30. 2026Privacy-Preserving Structureless Visual Localization via Image Obfuscationcited by 0
  31. 2026Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localizationcited by 0
  32. 2026Angle-I2P: Angle-Consistent-Aware Hierarchical Attention for Cross-Modality Outlier Rejectioncited by 0
  33. 2026Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regressioncited by 0
  34. 2026GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Trainingcited by 0
  35. 2026Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registrationcited by 0
  36. 2026OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registrationcited by 0