Cool stuff. Would it be hard to test it also on the feature matching like in LightGlue? Or directly 3D stuff like MapAnything?
arxiv.org/abs/2306.13643
map-anything.github.io
arxiv.org
LightGlue: Local Feature Matching at Light Speed
We introduce LightGlue, a deep neural network that learns to match local features across images. We revisit multiple design decisions of SuperGlue, the state of the art in sparse matching, and derive ...
