効率的に計算可能なBingham損失関数による確率的回転表現と姿勢推定への応用
Probabilistic Rotation Representation With an Efficiently Computable Bingham Loss Function and Its Application to Pose Estimation
Bingham分布の正規化定数の計算がボトルネックだった問題を解決するため、高速で実装が容易な損失関数を提案し、姿勢推定に応用した論文。
著者: Hiroya Sato, Takuya Ikeda, Koichi Nishiwaki
分類: cs.CV, cs.RO
原文アブストラクト
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.
