Probabilistic Rotation Representation With an Efficiently Computable Bingham Loss Function and Its Application to Pose Estimation

TL;DR

This paper introduces a fast, easy-to-compute loss function for the Bingham distribution, enabling uncertainty-aware rotation representation in deep learning-based pose estimation.

Contribution

It proposes a novel, efficient loss function for Bingham distribution, facilitating uncertainty modeling in rotation estimation tasks.

Findings

The new loss function is computationally efficient.

It improves pose estimation accuracy with uncertainty modeling.

The approach is applicable to deep learning frameworks.

Abstract

In recent years, a deep learning framework has been widely used for object pose estimation. While quaternion is a common choice for rotation representation of 6D pose, it cannot represent an uncertainty of the observation. In order to handle the uncertainty, Bingham distribution is one promising solution because this has suitable features, such as a smooth representation over SO(3), in addition to the ambiguity representation. However, it requires the complex computation of the normalizing constants. This is the bottleneck of loss computation in training neural networks based on Bingham representation. As such, we propose a fast-computable and easy-to-implement loss function for Bingham distribution. We also show not only to examine the parametrization of Bingham distribution but also an application based on our loss function.