cvlab-epfl / segmentation-driven-pose

Segmentation-driven 6D Object Pose Estimation. CVPR 2019.
GNU General Public License v3.0
184 stars 37 forks source link

what modulating factor do you use in confidence term? #4

Closed sjtuytc closed 5 years ago

alen0216056 commented 5 years ago

In my implementation, I used 0.5 in confidence term.(When the image space is normalized from [0, 1] to [0, 10]. The bigger value represent the stricter confidence term, I guess {1, 2, 3} are also good choices.

sjtuytc commented 5 years ago

thanks a lot!