HyperPosePDF Hypernetworks Predicting the Probability Distribution on SO(3)

Timon Höfer, Benjamin Kiefer, Martin Messmer, Andreas Zell

Abstract:

Pose estimation of objects in images is an essential prob-
lem in virtual and augmented reality and robotics. Tradi-
tional solutions use depth cameras, which can be expensive,
and working solutions require long processing times. This
work focuses on the more difficult task when only RGB in-
formation is available. To this end, we predict not only the
pose of an object but the complete probability density func-
tion (pdf) on the rotation manifold. This is the most general
way to approach the pose estimation problem and is partic-
ularly useful in analysing object symmetries. In this work,
we leverage implicit neural representations for the task of
pose estimation and show that hypernetworks can be used
to predict the rotational pdf. Furthermore, we analyse the
Fourier embedding on SO(3) and evaluate the effectiveness
of an initial Fourier embedding that proved successful. Our
HyperPosePDF outperforms the current SOTA approaches
on the SYMSOL dataset.