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
Thank you for public this repo.
In the code I see that we need to make sure the number of vertices the same between the source and the target mesh. However, for normal fusion process, the number of vertices will be changed. So I am wondering how will we control the number of vertices?
The text was updated successfully, but these errors were encountered:
Yes, it's true that during fusion the canonical shape is continuously updated, and the number of vertices in extracted mesh changes every time. However, for evaluation of tracking we require consistent meshes (over specific frame segments, e.g. 0-100, 0-200, 0-300, etc.). To cope with that, in our framework we extract the latest canonical mesh at each segment's end (e.g. at frame 200), and we deform it to every evaluation frame, to get consistent meshes at evaluation frames (e.g. 0, 50, 100, 150, 200).
Thank you for public this repo.
In the code I see that we need to make sure the number of vertices the same between the source and the target mesh. However, for normal fusion process, the number of vertices will be changed. So I am wondering how will we control the number of vertices?
The text was updated successfully, but these errors were encountered: