A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function
This work addresses a computational bottleneck in pose estimation for symmetric objects, offering an incremental improvement over existing methods.
The paper tackles the problem of ambiguous rotation representation in object pose estimation by introducing a fast-computable negative log-likelihood loss function for the Bingham distribution, enabling efficient capture of symmetric properties from point clouds.
In recent years, a deep learning framework has been widely used for object pose estimation. While quaternion is a common choice for rotation representation, it cannot represent the ambiguity of the observation. In order to handle the ambiguity, the Bingham distribution is one promising solution. However, it requires complicated calculation when yielding the negative log-likelihood (NLL) loss. An alternative easy-to-implement loss function has been proposed to avoid complex computations but has difficulty expressing symmetric distribution. In this paper, we introduce a fast-computable and easy-to-implement NLL loss function for Bingham distribution. We also create the inference network and show that our loss function can capture the symmetric property of target objects from their point clouds.