Are Euler angles a useful rotation parameterisation for pose estimation with Normalizing Flows?
This addresses pose estimation in 3D computer vision, offering a simpler parameterization for probabilistic outputs, but it is incremental as it compares to existing methods.
The paper investigates whether Euler angles are a useful rotation parameterization for probabilistic pose estimation using Normalizing Flows, finding they can lead to effective models despite known limitations.
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.