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 are high-profile specialized packages for this task, mentioned in the above paper, such as Annoy, NMSLib, Faiss.
By comparison, FLANN, a fork of it integrated into OpenCV, looks very old and it's not maintained. It is suggested that in OpenCV 5, since we have an opportunity to clean the library, we will remove a separate module FLANN.
use Apache-2 licensed Spotify's Annoy library: https://github.com/spotify/annoy. Annoy contains just a few files and so it can also be put directly to OpenCV, without creating explicit opencv/3rdparty entry.
The upgraded 'mini FLANN' (nanoflann or Annoy) can be put to features2d where it logically belongs.
Probably, features2d should be renamed to features to reflect that it can be used not just for features extracted from 2D images. The current modern way to compute features is to run a deep learning model.
Additional context
No response
The text was updated successfully, but these errors were encountered:
Describe the feature and motivation
Approximate nearest-neighbor search is very important research and development area of today's AI technologies. Besides computer vision (e.g. in face or scene recognition applications), they are actively used for recommendation systems, e.g. https://www.benfrederickson.com/approximate-nearest-neighbours-for-recommender-systems/.
There are high-profile specialized packages for this task, mentioned in the above paper, such as Annoy, NMSLib, Faiss.
By comparison, FLANN, a fork of it integrated into OpenCV, looks very old and it's not maintained. It is suggested that in OpenCV 5, since we have an opportunity to clean the library, we will remove a separate module FLANN.
The following two options are suggested:
The upgraded 'mini FLANN' (nanoflann or Annoy) can be put to features2d where it logically belongs.
Probably, features2d should be renamed to features to reflect that it can be used not just for features extracted from 2D images. The current modern way to compute features is to run a deep learning model.
Additional context
No response
The text was updated successfully, but these errors were encountered: