Pose Estimation On Inloc
Metrics
Results
Performance results of various models on this benchmark
Model Name | Paper Title | Repository | ||||||
|---|---|---|---|---|---|---|---|---|
| SuperGlue | 49.0 | 68.7 | 80.8 | 53.4 | 77.1 | 82.4 | SuperGlue: Learning Feature Matching with Graph Neural Networks | |
| LoFTR | 47.5 | 72.2 | 84.8 | 54.2 | 74.8 | 82.5 | LoFTR: Detector-Free Local Feature Matching with Transformers | |
| GIM-LoFTR | 54.5 | 78.3 | 87.4 | 63.4 | 83.2 | 87.0 | GIM: Learning Generalizable Image Matcher From Internet Videos | - |
| DKM | 51.5 | 75.3 | 86.9 | 63.4 | 82.4 | 87.8 | DKM: Dense Kernelized Feature Matching for Geometry Estimation | - |
| GIM-DKM | 57.1 | 78.8 | 88.4 | 70.2 | 91.6 | 92.4 | GIM: Learning Generalizable Image Matcher From Internet Videos | - |
| GIM-SuperGlue | 53.5 | 76.8 | 86.9 | 61.8 | 85.5 | 87.8 | GIM: Learning Generalizable Image Matcher From Internet Videos | - |
0 of 6 row(s) selected.