Dense Pixel Correspondence Estimation On
Métriques
Viewpoint I AEPE
Viewpoint II AEPE
Viewpoint III AEPE
Viewpoint IV AEPE
Viewpoint V AEPE
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Viewpoint I AEPE | Viewpoint II AEPE | Viewpoint III AEPE | Viewpoint IV AEPE | Viewpoint V AEPE |
|---|---|---|---|---|---|
| optical-flow-estimation-using-a-spatial | 36.94 | 50.92 | 54.29 | 62.60 | 72.57 |
| dgc-net-dense-geometric-correspondence | 1.55 | 5.53 | 8.98 | 11.66 | 16.70 |
| cotr-correspondence-transformer-for-matching | 7.98 | - | - | - | - |
| deepmatching-hierarchical-deformable-dense | 5.84 | 4.63 | 12.43 | 12.17 | 22.55 |
| deep-matching-prior-test-time-optimization | 0.48 | 2.24 | 2.41 | 4.32 | 5.16 |
| pwc-net-cnns-for-optical-flow-using-pyramid | 4.43 | 11.44 | 15.47 | 20.17 | 28.30 |
| cotr-correspondence-transformer-for-matching | 7.75 | - | - | - | - |
| flownet-20-evolution-of-optical-flow | 5.99 | 15.55 | 17.09 | 22.13 | 30.68 |