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 see that the objectness and plane-fitting score calculations follow different equations in the code and v1 and v2 of the SceneCut paper.Are either of them known to perform better than the other?
To compute objectness as in v2 of the paper :
Would it be possible to explain how to extract the b_ext and b_int and also RL(Region level) from the features?
Similarly, for the plane-fitting scores, which version is known to perform best?
Thanks!
The text was updated successfully, but these errors were encountered:
I see that the objectness and plane-fitting score calculations follow different equations in the code and v1 and v2 of the SceneCut paper.Are either of them known to perform better than the other?
To compute objectness as in v2 of the paper :
Would it be possible to explain how to extract the b_ext and b_int and also RL(Region level) from the features?
Similarly, for the plane-fitting scores, which version is known to perform best?
Thanks!
The text was updated successfully, but these errors were encountered: