search

mihaidusmanu / d2-net

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Other
761 stars 163 forks source link

The results of Superpoint #76

Closed pixelsmaker closed 3 years ago

pixelsmaker commented 3 years ago

Did you get the superpoint.npy in cache by using Superpoint-officially-pretrained model to extract features on the original image resolution, not 240320 or 480640 resolution? Or you retrain the Superpoint model ?

mihaidusmanu commented 3 years ago

We use the official pretrained model on full resolution similar to other works (e.g., SuperGlue). All other parameters are the same as in the official repository.