PoseRBPF: A Rao-Blackwellized Particle Filter for 6-D Object Pose Tracking

Tracking 6-D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this article, we formulate the 6-D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3-D rotation and the 3-D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF, to efficiently estimate the 3-D translation of an object along with the full distribution over the 3-D rotation. This is achieved by discretizing the rotation space in a fine-grained manner and training an autoencoder network to construct a codebook of feature embeddings for the discretized rotations. As a result, PoseRBPF can track objects with arbitrary symmetries while still maintaining adequate posterior distributions. Our approach achieves state-of-the-art results on two 6-D pose estimation benchmarks. We open-source our implementation at https://github.com/NVlabs/PoseRBPF.

Automated summary

The PoseRBPF method proposed in this article efficiently estimates the pose of an object by decoupling 3-D rotation and 3-D translation in the Rao-Blackwellized particle filtering framework. By discretizing the rotation space in a fine-grained manner, training an autoencoder network, and constructing a codebook of feature embeddings, it can track objects with arbitrary symmetries.