mlsanityData to 7 Oct 2026

Learning to Match Features with Seeded Graph Matching Network

arXiv 2108.08771 ↗First posted 19 Aug 2021cs.CVcited by 92

Not on the map. Why?

Abstract (arXiv)

Matching local features across images is a fundamental problem in computer vision. Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching Network, a graph neural network with sparse structure to reduce redundant connectivity and learn compact representation. The network consists of 1) Seeding Module, which initializes the matching by generating a small set of reliable matches as seeds. 2) Seeded Graph Neural Network, which utilizes seed matches to pass messages within/across images and predicts assignment costs. Three novel operations are proposed as basic elements for message passing: 1) Attentional Pooling, which aggregates keypoint features within the image to seed matches. 2) Seed Filtering, which enhances seed features and exchanges messages across images. 3) Attentional Unpooling, which propagates seed features back to original keypoints. Experiments show that our method reduces computational and memory complexity significantly compared with typical attention-based networks while competitive or higher performance is achieved.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

44 of 66 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  5. 2020Reformer: The Efficient Transformercited by 1,658
  6. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  7. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  10. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  11. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  12. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
32 more
  1. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  2. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  3. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  4. 2016LIFT: Learned Invariant Feature Transformcited by 305
  5. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  6. 2020Sparse Sinkhorn Attentioncited by 250
  7. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  8. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  9. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  10. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  11. 2017Learning to Find Good Correspondencescited by 176
  12. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  13. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  14. 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 129
  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. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  18. 2019Learning Combinatorial Embedding Networks for Deep Graph Matchingcited by 98
  19. 2020Visibility-aware Multi-view Stereo Networkcited by 97
  20. 2020Deep Graph Matching Consensuscited by 85
  21. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  22. 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
  23. 2018GeoDesc: Learning Local Descriptors by Integrating Geometry Constraintscited by 52
  24. 2020RANSAC-Flow: generic two-stage image alignmentcited by 48
  25. 2020KFNet: Learning Temporal Camera Relocalization using Kalman Filteringcited by 43
  26. 2020Second-Order Pooling for Graph Neural Networkscited by 33
  27. 2021Learning Camera Localization via Dense Scene Matchingcited by 28
  28. 2018Matchable Image Retrieval by Learning from Surface Reconstructioncited by 19
  29. 2019An Evaluation of Feature Matchers for Fundamental Matrix Estimationcited by 18
  30. 2020Learning to Guide Local Feature Matchescited by 6
  31. 2013Spectral Clustering for Divide-and-Conquer Graph Matchingcited by 5
  32. 2020Learning Stereo Matchability in Disparity Regression Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 13; 2023: 25; 2024: 21; 2025: 21; 2026: 12.

92 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  3. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  4. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  5. 2022QuadTree Attention for Vision Transformerscited by 129
  6. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  7. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  8. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
  9. 2023Detector-Free Structure from Motioncited by 71
  10. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 65
  11. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  12. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
38 more
  1. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  2. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
  3. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 43
  4. 2025MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Trainingcited by 40
  5. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  6. 2022TopicFM: Robust and Interpretable Topic-Assisted Feature Matchingcited by 32
  7. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  8. 2022ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attentioncited by 29
  9. 2022Decoupling Makes Weakly Supervised Local Feature Bettercited by 28
  10. 2023SFD2: Semantic-guided Feature Detection and Descriptioncited by 28
  11. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  12. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 25
  13. 2023Adaptive Spot-Guided Transformer for Consistent Local Feature Matchingcited by 22
  14. 2026VGGT-Omegacited by 20
  15. 2023DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matchingcited by 18
  16. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 18
  17. 2024MESA: Matching Everything by Segmenting Anythingcited by 16
  18. 20223DG-STFM: 3D Geometric Guided Student-Teacher Feature Matchingcited by 14
  19. 2025JamMa: Ultra-lightweight Local Feature Matching with Joint Mambacited by 14
  20. 2024Towards Foundation Models for 3D Vision: How Close Are We?cited by 13
  21. 2025CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matchingcited by 12
  22. 2023Two-View Geometry Scoring Without Correspondencescited by 11
  23. 2024Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matchingcited by 11
  24. 2025G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integrationcited by 11
  25. 2023IMP: Iterative Matching and Pose Estimation with Adaptive Poolingcited by 10
  26. 2023TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matchingcited by 10
  27. 2023Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinementcited by 9
  28. 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
  29. 2025Multi-Resolution SAR and Optical Remote Sensing Image Registration Methods: A Review, Datasets, and Future Perspectivescited by 9
  30. 2022Improving Feature-based Visual Localization by Geometry-Aided Matchingcited by 8
  31. 2023LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signalscited by 8
  32. 2023Structured Epipolar Matcher for Local Feature Matchingcited by 8
  33. 2025RUBIK: A Structured Benchmark for Image Matching across Geometric Challengescited by 8
  34. 2026STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstructioncited by 8
  35. 2023OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matchingcited by 7
  36. 2024Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switchingcited by 7
  37. 2025EDM: Efficient Deep Feature Matchingcited by 7
  38. 2025CoMatcher: Multi-View Collaborative Feature Matchingcited by 7

50 most cited of 92 All 92 (JSON)