mlsanityData to 7 Oct 2026

Learning to Find Good Correspondences

arXiv 1711.05971 ↗First posted 16 Nov 2017cs.CVcited by 176

Not on the map. Why?

Abstract (arXiv)

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while imbuing it with global information, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data.

Key facts. Cited by 176 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 38; 2023: 42; 2024: 22; 2025: 20; 2026: 15.

176 papers.

Sort:

By area:

  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  2. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  3. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  4. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  5. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  6. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  7. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  8. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  9. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  10. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  11. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  12. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
38 more
  1. 2024Local All-Pair Correspondence for Point Trackingcited by 77
  2. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 65
  3. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  4. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  5. 2023SiLK -- Simple Learned Keypointscited by 54
  6. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  7. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  8. 2022Is Geometry Enough for Matching in Visual Localization?cited by 48
  9. 2021Progressive Correspondence Pruning by Consensus Learningcited by 46
  10. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  11. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  12. 2022IFOR: Iterative Flow Minimization for Robotic Object Rearrangementcited by 42
  13. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  14. 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
  15. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  16. 2022TopicFM: Robust and Interpretable Topic-Assisted Feature Matchingcited by 32
  17. 2023Doppelgangers: Learning to Disambiguate Images of Similar Structurescited by 32
  18. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  19. 2023Robust Outlier Rejection for 3D Registration with Variational Bayescited by 31
  20. 2022Generalized Differentiable RANSACcited by 30
  21. 2021Learning Camera Localization via Dense Scene Matchingcited by 28
  22. 2022A case for using rotation invariant features in state of the art feature matcherscited by 27
  23. 2022Densely Constrained Depth Estimator for Monocular 3D Object Detectioncited by 27
  24. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  25. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  26. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  27. 2023A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypointscited by 25
  28. 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 25
  29. 2021Generalizable Human Pose Triangulationcited by 24
  30. 2022LASER: LAtent SpacE Rendering for 2D Visual Localizationcited by 23
  31. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  32. 2021Robust Differentiable SVDcited by 19
  33. 2022End2End Multi-View Feature Matching with Differentiable Pose Optimizationcited by 19
  34. 2022ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinementcited by 18
  35. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  36. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  37. 2021DFM: A Performance Baseline for Deep Feature Matchingcited by 17
  38. 2022PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solvingcited by 17

50 most cited of 176 All 176 (JSON)