Probabilistic Rotation Representation With an Efficiently Computable Bingham Loss Function and Its Application to Pose Estimation
This work addresses the challenge of handling uncertainty in object pose estimation for robotics and computer vision applications, representing an incremental improvement by optimizing an existing method for a known bottleneck.
The paper tackles the problem of representing rotation uncertainty in pose estimation by proposing a fast-computable and easy-to-implement loss function for the Bingham distribution, which overcomes the bottleneck of complex normalizing constant computations, enabling efficient training of neural networks.
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.