search

tjiiv-cprg / EPro-PnP

[CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
https://www.youtube.com/watch?v=TonBodQ6EUU
Apache License 2.0
1.11k stars 107 forks source link

The way of using EPro-PnP-6DOF #37

Open Pr0tAgon1st opened 2 years ago

Pr0tAgon1st commented 2 years ago

Hello, I want to know how to use EPro-PnP-6DOF to get the detailed position and pose infomation(like x y z r p y) instead of distribution map？ Thank you！

Lakonik commented 2 years ago

Hi! During test time, we solve the PnP optimization problem to find the exact pose. Ideally, this should be the optimal pose corresponding to the location with maximum distribution density. https://github.com/tjiiv-cprg/EPro-PnP/blob/1545131fde2b47ec4c135776d575e11feeb0f7cd/EPro-PnP-6DoF/lib/test.py#L210-L211