mlsanityData to 7 Oct 2026

LightGlue: Local Feature Matching at Light Speed

arXiv 2306.13643 ↗First posted 23 Jun 2023cs.CVcited by 583

Not on the map. Why?

Abstract (arXiv)

We introduce LightGlue, a deep neural network that learns to match local features across images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse matching, and derive simple but effective improvements. Cumulatively, they make LightGlue more efficient - in terms of both memory and computation, more accurate, and much easier to train. One key property is that LightGlue is adaptive to the difficulty of the problem: the inference is much faster on image pairs that are intuitively easy to match, for example because of a larger visual overlap or limited appearance change. This opens up exciting prospects for deploying deep matchers in latency-sensitive applications like 3D reconstruction. The code and trained models are publicly available at https://github.com/cvg/LightGlue.

Key facts. Cited by 583 papers in the map (data through 7 Oct 2026). Builds on 57 of its 84 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

57 of 84 references.

References · 57

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  6. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  7. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  8. 2020Reformer: The Efficient Transformercited by 1,658
  9. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  10. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  11. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  12. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
38 more
  1. 2018Self-Attention with Relative Position Representationscited by 1,112
  2. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  3. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  5. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  6. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  7. 2018Computational Optimal Transportcited by 765
  8. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  9. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  10. 2018Universal Transformerscited by 613
  11. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  12. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  13. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  14. 2020DISK: Learning local features with policy gradientcited by 310
  15. 2016LIFT: Learned Invariant Feature Transformcited by 305
  16. 2022Confident Adaptive Language Modelingcited by 297
  17. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  18. 2019Depth-Adaptive Transformercited by 227
  19. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  20. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  21. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  22. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  23. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  24. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  25. 2017Learning to Find Good Correspondencescited by 176
  26. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  27. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  28. 2021Self-attention Does Not Need O(n2) Memorycited by 152
  29. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  30. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  31. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  32. 2018MAGSAC: marginalizing sample consensuscited by 122
  33. 2016Spatially Adaptive Computation Time for Residual Networkscited by 118
  34. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  35. 2021Learnable Fourier Features for Multi-Dimensional Spatial Positional Encodingcited by 93
  36. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  37. 2019Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inferencecited by 91
  38. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 25; 2024: 135; 2025: 206; 2026: 217.

583 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  4. 20243D Reconstruction with Spatial Memorycited by 269
  5. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  6. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  7. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  8. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  9. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  10. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  11. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
  12. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
38 more
  1. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  2. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  3. 2023Detector-Free Structure from Motioncited by 71
  4. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  5. 2024Deep Patch Visual SLAMcited by 68
  6. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  7. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  8. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  9. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  10. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  11. 2023Dense Optical Tracking: Connecting the Dotscited by 58
  12. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  13. 2025UniGoal: Towards Universal Zero-shot Goal-oriented Navigationcited by 56
  14. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
  15. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  16. 2025Light3R-SfM: Towards Feed-forward Structure-from-Motioncited by 47
  17. 2024XoFTR: Cross-modal Feature Matching Transformercited by 45
  18. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 44
  19. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 43
  20. 2024Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignmentcited by 42
  21. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 40
  22. 2025MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Trainingcited by 40
  23. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 39
  24. 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesiscited by 39
  25. 2024DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detectorcited by 38
  26. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 38
  27. 2023Tracking and Mapping in Medical Computer Vision: A Reviewcited by 36
  28. 2024V-IRL: Grounding Virtual Intelligence in Real Lifecited by 35
  29. 2025UFM: A Simple Path towards Unified Dense Correspondence with Flowcited by 35
  30. 2024Control Color: Multimodal Diffusion-based Interactive Image Colorizationcited by 33
  31. 2026DreamX-World 1.0: A General-Purpose Interactive World Modelcited by 33
  32. 2025WinT3R: Window-Based Streaming Reconstruction with Camera Token Poolcited by 32
  33. 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splattingcited by 31
  34. 2024Reconstructing People, Places, and Camerascited by 31
  35. 2023360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queriescited by 28
  36. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  37. 2025Dynamic Camera Poses and Where to Find Themcited by 26
  38. 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 25

50 most cited of 583 All 583 (JSON)