pytorch-superpoint icon indicating copy to clipboard operation
pytorch-superpoint copied to clipboard

Published 20 hours ago • verified publisher icon eric-yyjau

Is there one less training step?

Open zyxzyx45 opened this issue 6 months ago • 1 comments

I think that after labeling the false truth value, do you still need to continue to train the feature point extraction network MagicPoint for this label, and then train the loss of the descriptor, that is, Superpoint, why do you directly train Superpoint after labeling?

zyxzyx45 avatar Aug 14 '24 06:08 zyxzyx45