Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SuperGlue

SuperGlue

Reported on 23 benchmarks across 5 tasks · 1 paper · 23 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision11 results

Visual LocalizationonAachen Day-Night v1.1 Benchmark
Acc@0.25m, 2°· 2019-11-26
77
best: 79.1 (GIM-LoFTR)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Visual LocalizationonAachen Day-Night v1.1 Benchmark
Acc@0.5m, 5°· 2019-11-26
90.6
best: 91.6 (GIM-LoFTR)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Visual LocalizationonAachen Day-Night v1.1 Benchmark
Acc@5m, 10°· 2019-11-26
100
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Pose EstimationonInLoc
DUC1-Acc@0.25m,10°· 2019-11-26
49
best: 57.1 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Pose EstimationonInLoc
DUC1-Acc@0.5m,10°· 2019-11-26
68.7
best: 78.8 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Pose EstimationonInLoc
DUC1-Acc@1.0m,10°· 2019-11-26
80.8
best: 88.4 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Pose EstimationonInLoc
DUC2-Acc@0.25m,10°· 2019-11-26
53.4
best: 70.2 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Pose EstimationonInLoc
DUC2-Acc@0.5m,10°· 2019-11-26
77.1
best: 91.6 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Pose EstimationonInLoc
DUC2-Acc@1.0m,10°· 2019-11-26
82.4
best: 92.4 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Image MatchingonIMC PhotoTourism
mean average accuracy @ 10· uses extra data· 2019-11-26
0.65248
best: 0.65606 (Harris Corner)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
Image MatchingonZEB
Mean AUC@5°· 2019-11-26
31.2
best: 53.3 (GIM-RoMa)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763

Methodology6 results

3DonInLoc
DUC1-Acc@0.25m,10°· 2019-11-26
49
best: 57.1 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
3DonInLoc
DUC1-Acc@0.5m,10°· 2019-11-26
68.7
best: 78.8 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
3DonInLoc
DUC1-Acc@1.0m,10°· 2019-11-26
80.8
best: 88.4 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
3DonInLoc
DUC2-Acc@0.25m,10°· 2019-11-26
53.4
best: 70.2 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
3DonInLoc
DUC2-Acc@0.5m,10°· 2019-11-26
77.1
best: 91.6 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
3DonInLoc
DUC2-Acc@1.0m,10°· 2019-11-26
82.4
best: 92.4 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763

Audio6 results

1 Image, 2*2 StitchionInLoc
DUC1-Acc@0.25m,10°· 2019-11-26
49
best: 57.1 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
1 Image, 2*2 StitchionInLoc
DUC1-Acc@0.5m,10°· 2019-11-26
68.7
best: 78.8 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
1 Image, 2*2 StitchionInLoc
DUC1-Acc@1.0m,10°· 2019-11-26
80.8
best: 88.4 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
1 Image, 2*2 StitchionInLoc
DUC2-Acc@0.25m,10°· 2019-11-26
53.4
best: 70.2 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
1 Image, 2*2 StitchionInLoc
DUC2-Acc@0.5m,10°· 2019-11-26
77.1
best: 91.6 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763
1 Image, 2*2 StitchionInLoc
DUC2-Acc@1.0m,10°· 2019-11-26
82.4
best: 92.4 (GIM-DKM)
SOTA
SuperGlue: Learning Feature Matching with Graph Neural Networks arXiv:1911.11763