mlsanityData to 14 Oct 2026

SuperGlue: Learning Feature Matching with Graph Neural Networks

arXiv 1911.11763 ↗First posted 26 Nov 2019cs.CVcited by 1,443

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D world through end-to-end training from image pairs. SuperGlue outperforms other learned approaches and achieves state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. The proposed method performs matching in real-time on a modern GPU and can be readily integrated into modern SfM or SLAM systems. The code and trained weights are publicly available at https://github.com/magicleap/SuperGluePretrainedNetwork.

Key facts. Cited by 1,443 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 133; 2022: 202; 2023: 282; 2024: 257; 2025: 325; 2026: 244.

1,443 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  3. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  4. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  5. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  6. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  7. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  8. 2021SimVLM: Simple Visual Language Model Pretraining with Weak Supervisioncited by 647
  9. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  10. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  11. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  12. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
38 more
  1. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 327
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  3. 2023RoMa: Robust Dense Feature Matchingcited by 302
  4. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  5. 20243D Reconstruction with Spatial Memorycited by 277
  6. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 275
  7. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  8. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  9. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  10. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  11. 2023Language is All a Graph Needscited by 220
  12. 2024Global Structure-from-Motion Revisitedcited by 218
  13. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  14. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  15. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  16. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  17. 2022Deep Patch Visual Odometrycited by 190
  18. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  19. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  20. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  21. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 177
  22. 2024RegMix: Data Mixture as Regression for Language Model Pre-trainingcited by 177
  23. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  24. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  25. 2021SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequencescited by 163
  26. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  27. 2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 161
  28. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  29. 2026Advancing Open-source World Modelscited by 154
  30. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  31. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 152
  32. 2023Chain of Hindsight Aligns Language Models with Feedbackcited by 148
  33. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  34. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  35. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  36. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  37. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  38. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131

50 most cited of 1,443 All 1,443 (JSON)