Are Euler angles a useful rotation parameterisation for pose estimation with Normalizing Flows?

TL;DR

This paper investigates whether Euler angles are a practical and effective parameterization for probabilistic 3D pose estimation using Normalizing Flows, considering their simplicity despite known limitations.

Contribution

The study evaluates the potential of Euler angles as a basis for Normalizing Flows in pose estimation, highlighting their advantages over more complex parameterizations.

Findings

Euler angles can be effectively used with Normalizing Flows for pose estimation.

Euler angles offer computational simplicity despite their known issues.

The approach provides a probabilistic pose output beneficial in ambiguous scenarios.

Abstract

Object pose estimation is a task that is of central importance in 3D Computer Vision. Given a target image and a canonical pose, a single point estimate may very often be sufficient; however, a probabilistic pose output is related to a number of benefits when pose is not unambiguous due to sensor and projection constraints or inherent object symmetries. With this paper, we explore the usefulness of using the well-known Euler angles parameterisation as a basis for a Normalizing Flows model for pose estimation. Isomorphic to spatial rotation, 3D pose has been parameterized in a number of ways, either in or out of the context of parameter estimation. We explore the idea that Euler angles, despite their shortcomings, may lead to useful models in a number of aspects, compared to a model built on a more complex parameterisation.