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
1.1k stars 104 forks source link

Ask about orientation data #29

Open a1445605672 opened 2 years ago

a1445605672 commented 2 years ago

First of all, I congratulate you on winning the honor of cvpr2022 best student paper. I am very confused about generating the probability density, whether the peak of the probability density is the coordinates of the object, I made some annotations in the figure below. 01

Lakonik commented 2 years ago

Hi! The PnP solver is meant to find the optimal pose with highest probability density. Although in practice the solution might fall into a local optimum, e.g., a smaller peak, depending on the initial pose.