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
There is no easy way to get detection scores out of VLFeat. The current approach is very hacky and bug-prone as I recover the scores directly from the DoG pyramid. The following line should be thoroughly verified.
How about making this change inside COLMAP? We can extend the FeatureKeypoint struct with a score and also extend the SQLite database schema with an extra column.
There is no easy way to get detection scores out of VLFeat. The current approach is very hacky and bug-prone as I recover the scores directly from the DoG pyramid. The following line should be thoroughly verified.
https://github.com/mihaidusmanu/pycolmap/blob/61fbe2748a15717fcbeaee717fb5a1405f978c34/sift.cc#L102
The text was updated successfully, but these errors were encountered: