Image Matching On Imc Phototourism
Metrics
mean average accuracy @ 10
Results
Performance results of various models on this benchmark
Model Name | mean average accuracy @ 10 | Paper Title | Repository |
|---|---|---|---|
| SuperGlue | 0.65248 | SuperGlue: Learning Feature Matching with Graph Neural Networks | |
| Harris Corner | 0.65606 | HarrisZ$^+$: Harris Corner Selection for Next-Gen Image Matching Pipelines | - |
| RootSIFT | 0.59859 | Three things everyone should know to improve object retrieval | |
| Key.Net-SOSNet | 0.60285 | Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters | |
| DISK | 0.65435 | DISK: Learning local features with policy gradient | |
| DoG-AffNet-HardNet8 | 0.64212 | Repeatability Is Not Enough: Learning Affine Regions via Discriminability | |
| D2-Net (MS) | 0.36285 | D2-Net: A Trainable CNN for Joint Detection and Description of Local Features | |
| R2D2 | 0.56345 | R2D2: Reliable and Repeatable Detector and Descriptor |
0 of 8 row(s) selected.