Visual Localization On Aachen Day Night V1 1
评估指标
Acc@0.25m, 2°
Acc@0.5m, 5°
Acc@5m, 10°
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||||
|---|---|---|---|---|---|
| GIM-LoFTR | 79.1 | 91.6 | 100.0 | GIM: Learning Generalizable Image Matcher From Internet Videos | |
| LoFTR | 78.5 | 90.6 | 99.0 | LoFTR: Detector-Free Local Feature Matching with Transformers | |
| GIM-SuperGlue | 78.0 | 90.6 | 100.0 | GIM: Learning Generalizable Image Matcher From Internet Videos | |
| GIM-DKM | 77.0 | 90.1 | 99.5 | GIM: Learning Generalizable Image Matcher From Internet Videos | |
| SuperGlue | 77.0 | 90.6 | 100.0 | SuperGlue: Learning Feature Matching with Graph Neural Networks | |
| SCFeat | 74.3 | 89 | 98.4 | Shared Coupling-bridge for Weakly Supervised Local Feature Learning | |
| DKM | 70.2 | 90.1 | 97.4 | DKM: Dense Kernelized Feature Matching for Geometry Estimation |
0 of 7 row(s) selected.