mlsanityData to 7 Oct 2026

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

arXiv 1704.05939 ↗First posted 19 Apr 2017cs.CVcited by 261

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel benchmark for evaluating local image descriptors. We demonstrate that the existing datasets and evaluation protocols do not specify unambiguously all aspects of evaluation, leading to ambiguities and inconsistencies in results reported in the literature. Furthermore, these datasets are nearly saturated due to the recent improvements in local descriptors obtained by learning them from large annotated datasets. Therefore, we introduce a new large dataset suitable for training and testing modern descriptors, together with strictly defined evaluation protocols in several tasks such as matching, retrieval and classification. This allows for more realistic, and thus more reliable comparisons in different application scenarios. We evaluate the performance of several state-of-the-art descriptors and analyse their properties. We show that a simple normalisation of traditional hand-crafted descriptors can boost their performance to the level of deep learning based descriptors within a realistic benchmarks evaluation.

Key facts. Cited by 261 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 39; 2023: 57; 2024: 43; 2025: 46; 2026: 38.

261 papers.

Sort:

By area:

  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  2. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  3. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  4. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  5. 2023Emergent Correspondence from Image Diffusioncited by 437
  6. 2023RoMa: Robust Dense Feature Matchingcited by 296
  7. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 281
  8. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 258
  9. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  10. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  11. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  12. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
38 more
  1. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
  2. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  3. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  4. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  5. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  6. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
  7. 2024GIM: Learning Generalizable Image Matcher From Internet Videoscited by 72
  8. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  9. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 65
  10. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  11. 2024MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Modelscited by 61
  12. 2022DeepLSD: Line Segment Detection and Refinement with Deep Image Gradientscited by 58
  13. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
  14. 2023SiLK -- Simple Learned Keypointscited by 54
  15. 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotationscited by 53
  16. 2023Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmarkcited by 51
  17. 2023CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representationcited by 45
  18. 2024XoFTR: Cross-modal Feature Matching Transformercited by 45
  19. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  20. 2021Warp Consistency for Unsupervised Learning of Dense Correspondencescited by 42
  21. 2022BALF: Simple and Efficient Blur Aware Local Feature Detectorcited by 34
  22. 2022TopicFM: Robust and Interpretable Topic-Assisted Feature Matchingcited by 32
  23. 2021Deep Matching Prior: Test-Time Optimization for Dense Correspondencecited by 30
  24. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  25. 2024Cross-View Completion Models are Zero-shot Correspondence Estimatorscited by 30
  26. 2023PMatch: Paired Masked Image Modeling for Dense Geometric Matchingcited by 29
  27. 2022Decoupling Makes Weakly Supervised Local Feature Bettercited by 28
  28. 2022A case for using rotation invariant features in state of the art feature matcherscited by 27
  29. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  30. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  31. 2025MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Trainingcited by 24
  32. 2021ELSED: Enhanced Line SEgment Drawingcited by 23
  33. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  34. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  35. 2023Adaptive Spot-Guided Transformer for Consistent Local Feature Matchingcited by 22
  36. 2021NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learningcited by 21
  37. 2023Diffusion Model for Dense Matchingcited by 21
  38. 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21

50 most cited of 261 All 261 (JSON)