You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I would like to ask is that specially use a OriNet to rotate the patch, and then extract descriptor from the rotated patch necessary? I think most of descriptors are, at least claimed to be, rotation invariant.
descriptor(rotate(raw_patch)) and descriptor(raw_patch), are they really differ much?
The text was updated successfully, but these errors were encountered:
So far, I am not aware of any practically good "rotationally invariant descriptors". What is true, that if you rotate patch to small angle, like 5..may be 10 degrees, you would be able to match them. If more - no way.
Hi, I think your paper can be understood as a decoupled spatial transformer network (when STN uses affine matrix), but the way you do affine shape parametrization is much more precise and may lead to higher accuracy.
Hi thanks for the repo!
I would like to ask is that specially use a OriNet to rotate the patch, and then extract descriptor from the rotated patch necessary? I think most of descriptors are, at least claimed to be, rotation invariant.
descriptor(rotate(raw_patch)) and descriptor(raw_patch), are they really differ much?
The text was updated successfully, but these errors were encountered: