preprint · arXiv (Cornell University) · 2023

A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function

Cited by 0Open access

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, 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.

Cite this paper

APA 7

Sato, H., Ikeda, T., & Nishiwaki, K. (2023). A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.18947

MLA 9

Sato, H., et al. “A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function.” arXiv (Cornell University), 2023, https://doi.org/10.48550/arxiv.2305.18947.

Chicago

Sato, H., Takuya Ikeda, and Koichi Nishiwaki. 2023. “A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.18947.

Harvard

Sato, H., Ikeda, T. and Nishiwaki, K. (2023) ‘A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.2305.18947.

BibTeX

@misc{sato2023probabilistic,
  title = {{A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function}},
  author = {Sato, H. and Ikeda, Takuya and Nishiwaki, Koichi},
  journal = {arXiv (Cornell University)},
  year = {2023},
  doi = {10.48550/arxiv.2305.18947}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.