Papers › SuperGlue: Learning Feature Matching with Graph Neural Networks

SuperGlue: Learning Feature Matching with Graph Neural Networks

26 Nov 2019CVPR 2020 6arXiv:1911.11763archive 2025-07-28

Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (magicleap/SuperGluePretrainedNetwork) was not harvested; the 22 samples below come from 5 community repositories.

Syntology 22 code samples harvested from 5 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 22 samples from 5 repositories, 16 ran (11 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

19 repositories listed; official and paper-mentioned ones first.

magicleap/SuperGluePretrainedNetwork officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
AwaleSajil/SuperGlue_Demo_Modified1 mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
HeatherJiaZG/SuperGlue-pytorch mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
JeeseongKim/SuperGlue mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Thinklab-SJTU/PCA-GM mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Thinklab-SJTU/ThinkMatch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers (arXiv:2003.11657; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
borglab/gtsfm mentioned on GitHubNOASSERTIONSyntology: not harvested report
calipos/SuperGlue_NCNN mentioned on GitHubSyntology: not harvested report
cvg/Hierarchical-Localization mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ImLoc: Revisiting Visual Localization with Image-based Representation (arXiv:2601.04185; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
jomariya23156/SuperGlue-for-Visual-Place-Recognition mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
nodarsensor/medium-keypoint-autocal mentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
rogerwwww/PCA-GM mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
tzvikif/SuperGlue mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ucuapps/openglue mentioned on GitHubpytorchMITSyntology: 9 samples, 6 ran (0 instrument-failed) · 3 unverified report
vdvchen/sgmnet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
xlearning-scu/2023-iccv-common mentioned on GitHubpytorchNOASSERTIONSyntology: 5 samples, 4 ran (4 instrument-failed) · 1 unverified report
zju3dv/LoFTR mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoFTR: Detector-Free Local Feature Matching with Transformers (arXiv:2104.00680; that paper's own run record: 14 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
gouthamvgk/SuperGlue_training pytorchNOASSERTIONSyntology: not harvested report
huggingface/transformers pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

22 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
2ran; the contract check could not run
10ran
6unverified

Licence: 6 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

nodarsensor/medium-keypoint-autocal community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
get_ORB_keypoints run_keypoint_autocal.py ran MIT (permissive) · ba150e661e7879da · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int, max_keypoints:int/0/int · returned tuple · level recorded 2026-09-24
get_disparity keypoint_utils.py ran MIT (permissive) · 14b3ae26bfe9685b · report fixture: signature left:ndarray/3/int, right:ndarray/3/int, maxDisparity:int/0/int · returned ndarray · level recorded 2026-09-24
read in 34 papers keypoint_utils.py ran MIT (permissive) · 29dea47dffb92051 · report fixture: signature pathname:str/0/str · returned tuple · level recorded 2026-09-24
rectify in 5 papers keypoint_utils.py ran MIT (permissive) · 1605faf3d7529a14 · report fixture: signature left:ndarray/2/int, right:ndarray/2/int, K1:ndarray/2/float, distCoeffs1:ndarray/1/float, K2:ndarray/2/float, distCoeffs2:ndarray/1/float, R:ndarray/2/float, T:ndarray/2/float · returned tuple · level recorded 2026-09-24
get_SIFT_keypoints run_keypoint_autocal.py unverified MIT (permissive) · 384f114063c3f185 · report
get_SuperGlue_keypoints run_keypoint_autocal.py unverified MIT (permissive) · 7fbb2268e4b51bf6 · report
tzvikif/SuperGlue community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
scale_H demo_superglue.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 29fcca902e5d12cf · report fixture: signature H:ndarray/2/float, orig_image_size:tuple/1/int, new_image_size:tuple/1/int · returned ndarray · level recorded 2026-09-22
ucuapps/openglue community (archive-listed) 9 samples, 6 ran (0 instrument-failed) · 3 unverified
check_if_features_exist extract_features.py ran MIT (permissive) · 06246573d5b65142 · report fixture: signature output_path_scene:PosixPath/0/?, image_base_name:str/0/str · returned bool · level recorded 2026-09-24
get_images_list extract_features.py ran MIT (permissive) · 5e8ae53919706ac1 · report fixture: signature input_data_path:PosixPath/0/?, image_formats:list/1/str · returned list · level recorded 2026-09-24
get_output_directory_name extract_features.py ran MIT (permissive) · 7f4c7b4a1f1df8ed · report fixture: signature feature_extractor_config:dict/0/?, args:Namespace/0/? · returned str · level recorded 2026-09-24
matched_triplet_criterion utils/losses.py ran MIT (permissive) · 8951184b974ad292 · report fixture: signature dist:Tensor/3/float, margin:float/0/float, indexes:tuple/1/Tensor, mean_weights:Tensor/1/float · returned Tensor · level recorded 2026-09-24
preds_to_device inference.py ran MIT (permissive) · a8f4de29824b51ee · report fixture: signature preds:tuple/1/Tensor, device:str/0/str · returned tuple · level recorded 2026-09-24
unmatched_margin_criterion utils/losses.py ran MIT (permissive) · 7a7964f270ef78b6 · report fixture: signature dist:Tensor/3/float, margin:float/0/float, indexes:tuple/1/Tensor, mean_weights:Tensor/1/float, zero_to_one:bool/0/bool · returned Tensor · level recorded 2026-09-24
criterion in 14 papers utils/losses.py unverified MIT (permissive) · 94be4c45dc8984f4 · report
get_laf_to_sideinfo_converter models/laf_converter.py unverified MIT (permissive) · 1a7aa0b908a6c2f5 · report
load_torch_image inference.py unverified MIT (permissive) · 3cdd51bdc821f2d7 · report
vdvchen/sgmnet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
feed_match evaluation/evaluate.py ran · honoured contract MIT (permissive) · a1d64ab06770a931 · report fixture: signature info:dict/0/?, matcher:MockMatcher/0/? · returned list · level recorded 2026-09-22
xlearning-scu/2023-iccv-common community (archive-listed) 5 samples, 4 ran (4 instrument-failed) · 1 unverified
construct_sparse_aff_mat src/factorize_graph_matching.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 4fb4d2f6a656f770 · report fixture: signature Ke:Tensor/2/float, Kp:Tensor/2/float, row_idx:Tensor/1/int, col_idx:Tensor/1/int · returned tuple · level recorded 2026-09-22
kronecker_torch src/factorize_graph_matching.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 5e21b17e58bd4c27 · report fixture: signature t1:Tensor/3/float, t2:Tensor/3/float · returned Tensor · level recorded 2026-09-22
matching_precision src/evaluation_metric.py ran · our draft was wrong licence not identified · pointer only · a08c4eaa0b9abea0 · report fixture: signature pmat_pred:Tensor/3/float, pmat_gt:Tensor/3/float, ns:Tensor/1/int · returned Tensor · level recorded 2026-09-22
matching_recall src/evaluation_metric.py ran · our draft was wrong licence not identified · pointer only · a06dc4b720962ade · report fixture: signature pmat_pred:Tensor/3/float, pmat_gt:Tensor/3/float, ns:Tensor/1/int · returned Tensor · level recorded 2026-09-22
pck in 6 papers src/evaluation_metric.py unverified licence not identified · pointer only · 4ff16c7de0975ab1 · report

Tasks

Camera Pose EstimationGraph Neural NetworkImage MatchingPose EstimationVisual LocalizationVisual Place Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Matching IMC PhotoTourism SuperGlue mean average accuracy @ 10 0.65248 #3 of 8 Archive leaderboard report
Image Matching ZEB SuperGlue Mean AUC@5° 31.2 #10 of 10 Archive leaderboard report
Pose Estimation InLoc SuperGlue DUC1-Acc@0.25m,10° 49.0 #5 of 6 Archive leaderboard report
Pose Estimation InLoc SuperGlue DUC1-Acc@0.5m,10° 68.7 #5 of 6 Archive leaderboard report
Pose Estimation InLoc SuperGlue DUC1-Acc@1.0m,10° 80.8 #5 of 6 Archive leaderboard report
Pose Estimation InLoc SuperGlue DUC2-Acc@0.25m,10° 53.4 #5 of 6 Archive leaderboard report
Pose Estimation InLoc SuperGlue DUC2-Acc@0.5m,10° 77.1 #5 of 6 Archive leaderboard report
Pose Estimation InLoc SuperGlue DUC2-Acc@1.0m,10° 82.4 #5 of 6 Archive leaderboard report
Visual Localization Aachen Day-Night v1.1 Benchmark SuperGlue Acc@0.25m, 2° 77.0 #4 of 7 Archive leaderboard report
Visual Localization Aachen Day-Night v1.1 Benchmark SuperGlue Acc@0.5m, 5° 90.6 #4 of 7 Archive leaderboard report
Visual Localization Aachen Day-Night v1.1 Benchmark SuperGlue Acc@5m, 10° 100.0 #4 of 7 Archive leaderboard report
Visual Place Recognition Berlin Kudamm SuperPoint & SuperGlue Recall@1 59.64 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections