LightGlue: Local Feature Matching at Light Speed
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
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 github.com/cvg/LightGlue.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Fischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901 · cited 1×
“While classical algorithms rely on hand-crafted criteria and gradient statistics [41, 23, 4, 53], much of the recent research has focused on designing Convolutional Neural Networks (CNNs) for both detection [81, 16, 19, 52, 73] and description [42, 72].”
MethodORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015) · IEEE Transactions on Robotics · doi:10.1109/tro.2015.2463671 · Cited by 6,778 · cited 3×
“This opens up exciting prospects for deploying deep matchers in latency-sensitive applications like SLAM [45, 5] or re-constructing larger scenes from crowd-sourced data [25, 60, 39, 57].”
BackgroundStructure-from-Motion Revisited
Schonberger, J. L., & Frahm, J.-M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.445 · Cited by 6,433
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 1×
“Yet, since its initial publication, Transform-ers have been extensively studied, improved, and applied to numerous language [17, 51, 13] and vision [18, 6, 29] tasks.”
BackgroundMachine Learning for High-Speed Corner Detection
Rosten, E., & Drummond, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_34 · Cited by 4,555
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596 · cited 1×
“This opens up exciting prospects for deploying deep matchers in latency-sensitive applications like SLAM [45, 5] or re-constructing larger scenes from crowd-sourced data [25, 60, 39, 57].”
BackgroundSuperPoint: Self-Supervised Interest Point Detection and Description
DeTone, D., Malisiewicz, T., & Rabinovich, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00060 · Cited by 3,355
SuperGlue: Learning Feature Matching With Graph Neural Networks
Sarlin, P.-E., DeTone, D., Malisiewicz, T., & Rabinovich, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00499 · Cited by 2,830
Self-citationNetVLAD: CNN Architecture for Weakly Supervised Place Recognition
Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.572 · Cited by 2,584
Self-Attention with Relative Position Representations
Shaw, P., Uszkoreit, J., & Vaswani, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2074 · Cited by 2,505 · cited 1×
“While absolute sinusoidal [74] or learned encodings [17, 51] were initially prevalent, recent works have studied relative encodings [63, 67] to stabilize the training and better capture long-range dependencies.”
BackgroundRoFormer: Enhanced transformer with rotary position embedding
Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., & Liu, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127063 · Cited by 1,957
RoFormer: Enhanced Transformer with Rotary Position Embedding
Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., & Liu, Y. (2021) · arXiv · doi:10.48550/arxiv.2104.09864 · Cited by 1,952 · cited 4×
“While absolute sinusoidal [74] or learned encodings [17, 51] were initially prevalent, recent works have studied relative encodings [63, 67] to stabilize the training and better capture long-range dependencies.”
BackgroundMethodInfluentialLoFTR: Detector-Free Local Feature Matching with Transformers
Sun, J., Shen, Z., Wang, Y., Bao, H., & Zhou, X. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00881 · Cited by 1,719
Reformer: The Efficient Transformer
Kitaev, N., Kaiser, Ł., & Levskaya, A. (2020) · arXiv · doi:10.48550/arxiv.2001.04451 · Cited by 1,435
BranchyNet: Fast inference via early exiting from deep neural networks
Teerapittayanon, S., McDanel, B., & Kung, H. T. (2016) · 2016 23rd International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr.2016.7900006 · Cited by 1,326
LIFT: Learned Invariant Feature Transform
Yi, K. M., Trulls, E., Lepetit, V., & Fua, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_28 · Cited by 1,202
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Sivic, J., Torii, A., & Sattler, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00828 · Cited by 1,179
Self-citationMegaDepth: Learning Single-View Depth Prediction from Internet Photos
Li, Z., & Snavely, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00218 · Cited by 1,135
From Coarse to Fine: Robust Hierarchical Localization at Large Scale
Sarlin, P.-E., Cadena, C., Siegwart, R., & Dymczyk, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01300 · Cited by 1,044
Self-citationConcerning nonnegative matrices and doubly stochastic matrices
Sinkhorn, R., & Knopp, P. (1967) · Pacific Journal of Mathematics · doi:10.2140/pjm.1967.21.343 · Cited by 887
Computational Optimal Transport
Peyré, G., & Cuturi, M. (2019) · now publishers, Inc. eBooks · doi:10.1561/9781680835519 · Cited by 847
Chum, O., Matas, J., & Kittler, J. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-45243-0_31 · Cited by 843
LaMDA: Language Models for Dialog Applications
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.08239 · Cited by 778 · cited 1×
“Yet, since its initial publication, Transformers have been extensively studied, improved, and applied to numerous language [17, 51, 13] and vision [18, 6, 29] tasks.”
BackgroundBenchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Sattler, T., Maddern, W., Toft, C., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Sivic, J., et al. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00897 · Cited by 699 · cited 3×
“SuperGlue is highly effective for visual localization in challenging conditions [59, 55, 58, 57] and generalizes well to other tasks like aerial matching [83], object pose estimation [69], and even fish re-identification [47].”
BackgroundMethodSelf-citationLearning to Find Good Correspondences
Yi, K. M., Trulls, E., Ono, Y., Lepetit, V., Salzmann, M., & Fua, P. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00282 · Cited by 552
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Radenovic, F., Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00598 · Cited by 401
Image matching across wide baselines: From paper to practice
Jin, Y., Mishkin, D., Mishchuk, A., Matas, J., Fua, P., Yi, K. M., & Trulls, E. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01385-0 · Cited by 388
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
Tian, Y., Yu, X., Fan, B., Wu, F., Heijnen, H., & Balntas, V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01127 · Cited by 366
Learning Two-View Correspondences and Geometry Using Order-Aware Network
Zhang, J., Sun, D., Luo, Z., Yao, A., Zhou, L., Shen, T., Chen, Y., Liao, H., & Quan, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00594 · Cited by 343
Spatially Adaptive Computation Time for Residual Networks
Figurnov, M., Collins, M. D., Zhu, Y., Zhang, L., Huang, J., Vetrov, D., & Salakhutdinov, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.194 · Cited by 329
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose
Sarlin, P.-E., Unagar, A., Larsson, M., Germain, H., Toft, C., Larsson, V., Pollefeys, M., Lepetit, V., Hammarstrand, L., Kahl, F., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00326 · Cited by 297
Self-citationNot All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
Li, X., Liu, Z., Luo, P., Loy, C. C., & Tang, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.684 · Cited by 268
ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
Chen, H., Luo, Z., Zhou, L., Tian, Y., Zhen, M., Fang, T., McKinnon, D., Tsin, Y., & Quan, L. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19824-3_2 · Cited by 239
Two-View Geometry Estimation Unaffected by a Dominant Plane
Chum, O., Werner, T., & Matas, J. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.354 · Cited by 217
Learning to Match Features with Seeded Graph Matching Network
Chen, H., Luo, Z., Zhang, J., Zhou, L., Bai, X., Hu, Z., Tai, C.-L., & Quan, L. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00624 · Cited by 215
Anytime Stereo Image Depth Estimation on Mobile Devices
Wang, Y., Lai, Z., Huang, G., Wang, B. H., van der Maaten, L., Campbell, M., & Weinberger, K. Q. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794003 · Cited by 209
MatchFormer: Interleaving Attention in Transformers for Feature Matching
Wang, Q., Zhang, J., Yang, K., Peng, K., & Stiefelhagen, R. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-26313-2_16 · Cited by 189
OnePose: One-Shot Object Pose Estimation without CAD Models
Sun, J., Wang, Z., Zhang, S., He, X., Zhao, H., Zhang, G., & Zhou, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00670 · Cited by 177
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement
Lindenberger, P., Sarlin, P.-E., Larsson, V., & Pollefeys, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00593 · Cited by 172
Self-citationDynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
Verelst, T., & Tuytelaars, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00239 · Cited by 170
LaMAR: Benchmarking Localization and Mapping for Augmented Reality
Sarlin, P.-E., Dusmanu, M., Schönberger, J. L., Speciale, P., Gruber, L., Larsson, V., Mikšík, O., & Pollefeys, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20071-7_40 · Cited by 166
Self-citationMODS: Fast and robust method for two-view matching
Mishkin, D., Matas, J., & Perdoch, M. (2015) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2015.08.005 · Cited by 158
ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching
Shi, Y., Cai, J.-X., Shavit, Y., Mu, T., Feng, W., & Zhang, K. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01219 · Cited by 146
HPatches: A benchmark and evaluation of handcrafted and learned local descriptors
Balntas, V., Lenc, K., Vedaldi, A., Tuytelaars, T., Matas, J., & Mikolajczyk, K. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2915233 · Cited by 132
Online Invariance Selection for Local Feature Descriptors
Pautrat, R., Larsson, V., Oswald, M. R., & Pollefeys, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_42 · Cited by 97
Self-citationHandcrafted Outlier Detection Revisited
Cavalli, L., Larsson, V., Oswald, M. R., Sattler, T., & Pollefeys, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58529-7_45 · Cited by 93
Self-citationMatchable Image Retrieval by Learning from Surface Reconstruction
Shen, T., Luo, Z., Zhou, L., Zhang, R., Zhu, S., Fang, T., & Quan, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20887-5_26 · Cited by 57
Feature matching for multi-epoch historical aerial images
Zhang, L., Rupnik, E., & Marc Pierrot-deseilligny, A. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.10.008 · Cited by 46
Self-attention Does Not Need $O(n^2)$ Memory
Rabe, M. N., & Staats, C. (2021) · arXiv · doi:10.48550/arxiv.2112.05682 · Cited by 17
Re-Identification of Giant Sunfish using Keypoint Matching
Pedersen, M., Haurum, J. B., Moeslund, T. B., & Nyegaard, M. (2022) · Proceedings of the Northern Lights Deep Learning Workshop · doi:10.7557/18.6234 · Cited by 9
Cited by
Grounding Image Matching in 3D with MASt3R
Leroy, V., Cabon, Y., & Revaud, J. (2024) · arXiv · doi:10.48550/arxiv.2406.09756 · Cited by 309
“SuperGlue and similar approaches [51, 72] thus propose to perform global reasoning in the last pairing step leveraging stronger priors to guide matching, yet leaving the detection and description local.”
MethodGrounding Image Matching in 3D with MASt3R
Leroy, V., Cabon, Y., & Revaud, J. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-73220-1_5 · Cited by 305
Multimodal Remote Sensing Image Matching via Learning Features and Attention Mechanism
Zhang, Y., Lan, C., Zhang, H., Ma, G., & Li, H. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3348980 · Cited by 37
V-IRL: Grounding Virtual Intelligence in Real Life
Yang, J., Ding, R., Brown, E., Qi, X., & Xie, S. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72995-9_3 · Cited by 20
Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Agarwal, N., Ali, A., Bala, M., Balaji, Y., Barker, E., Cai, T., Chattopadhyay, P., Chen, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.03575 · Cited by 13
Metadata
- Authors
- Lindenberger, P., Sarlin, P.-E., & Pollefeys, M.
- Venue
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2023-10-01
- Pages
- 17581-17592
- OpenAlex
- W4390872507
- Cited by
- 943
- References
- 55
- FWCI
- 107.22
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.