Visual Place Recognition On Berlin Kudamm
Metrics
Recall@1
Results
Performance results of various models on this benchmark
Model Name | Recall@1 | Paper Title | Repository |
---|---|---|---|
SuperPoint & SuperGlue | 59.64 | SuperGlue: Learning Feature Matching with Graph Neural Networks | - |
HF-Net | 46.78 | From Coarse to Fine: Robust Hierarchical Localization at Large Scale | - |
NetVLAD | 38.21 | NetVLAD: CNN architecture for weakly supervised place recognition | - |
HEAPUtil | 61.07 | A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition | - |
0 of 4 row(s) selected.