mlsanityData to 14 Oct 2026

To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition

arXiv 2504.06116 ↗First posted 8 Apr 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Visual Place Recognition (VPR) is a critical task in computer vision, traditionally enhanced by re-ranking retrieval results with image matching. However, recent advancements in VPR methods have significantly improved performance, challenging the necessity of re-ranking. In this work, we show that modern retrieval systems often reach a point where re-ranking can degrade results, as current VPR datasets are largely saturated. We propose using image matching as a verification step to assess retrieval confidence, demonstrating that inlier counts can reliably predict when re-ranking is beneficial. Our findings shift the paradigm of retrieval pipelines, offering insights for more robust and adaptive VPR systems. The code is available at https://github.com/FarInHeight/To-Match-or-Not-to-Match.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 71 of its 99 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

71 of 99 references.

References · 71

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  6. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  7. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  8. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  9. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  10. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  11. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  12. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
38 more
  1. 2020DISK: Learning local features with policy gradientcited by 312
  2. 2023RoMa: Robust Dense Feature Matchingcited by 302
  3. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  4. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  5. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  6. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  7. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  8. 2023AnyLoc: Towards Universal Visual Place Recognitioncited by 163
  9. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
  10. 2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 161
  11. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 152
  12. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 129
  13. 2022QuadTree Attention for Vision Transformerscited by 129
  14. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  15. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
  16. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  17. 2023EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognitioncited by 111
  18. 2020Self-supervising Fine-grained Region Similarities for Large-scale Image Localizationcited by 110
  19. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  20. 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
  21. 2020VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Changecited by 101
  22. 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 93
  23. 2022Deep Visual Geo-localization Benchmarkcited by 84
  24. 2024GIM: Learning Generalizable Image Matcher From Internet Videoscited by 75
  25. 2024BoQ: A Place is Worth a Bag of Learnable Queriescited by 64
  26. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
  27. 2024CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognitioncited by 61
  28. 2025MegaLoc: One Retrieval to Place Them Allcited by 60
  29. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  30. 2018Night-to-Day Image Translation for Retrieval-based Localizationcited by 57
  31. 2023SiLK -- Simple Learned Keypointscited by 54
  32. 2024Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognitioncited by 49
  33. 2014Visual Instance Retrieval with Deep Convolutional Networkscited by 48
  34. 2022Correlation Verification for Image Retrievalcited by 47
  35. 2020CoMIR: Contrastive Multimodal Image Representation for Registrationcited by 45
  36. 2023Data-efficient Large Scale Place Recognition with Graded Similarity Supervisioncited by 43
  37. 2020Adaptive-Attentive Geolocalization from few queries: a hybrid approachcited by 39
  38. 2019Multi-Process Fusion: Visual Place Recognition Using Multiple Image Processing Methodscited by 38

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformercited by 8
  2. 2026FoundYou: A Unified Model for Personalized Segmentation and Retrievalcited by 0
  3. 2026AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognitioncited by 0