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

TL;DR

PoseRBPF introduces a Rao-Blackwellized particle filter that efficiently tracks 6D object poses by decoupling rotation and translation, using a learned feature codebook for accurate rotation estimation, achieving state-of-the-art results.

Contribution

The paper presents a novel Rao-Blackwellized particle filtering approach that decouples rotation and translation for 6D pose tracking, incorporating a learned feature codebook for rotation discretization.

Findings

Achieves state-of-the-art accuracy on 6D pose benchmarks.

Effectively handles objects with arbitrary symmetries.

Maintains comprehensive posterior distributions for pose estimation.

Abstract

Tracking 6D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this work, we formulate the 6D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3D rotation and the 3D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF, to efficiently estimate the 3D translation of an object along with the full distribution over the 3D rotation. This is achieved by discretizing the rotation space in a fine-grained manner, and training an auto-encoder 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 6D pose estimation benchmarks. A video showing the experiments can be found at https://youtu.be/lE5gjzRKWuA