Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds

TL;DR

This paper introduces PPF-Tracker, a novel framework for category-level articulated object pose tracking that leverages point pair features and SE(3) invariance to improve robustness and generalization in complex environments.

Contribution

The work proposes a new pose tracking method using point pair features and SE(3) quasi-canonicalization, addressing challenges in articulated object pose estimation.

Findings

Demonstrates strong generalization on synthetic and real datasets.

Shows robustness in multi-frame pose tracking of articulated objects.

Outperforms existing methods in challenging scenarios.

Abstract

Articulated objects are prevalent in daily life and robotic manipulation tasks. However, compared to rigid objects, pose tracking for articulated objects remains an underexplored problem due to their inherent kinematic constraints. To address these challenges, this work proposes a novel point-pair-based pose tracking framework, termed \textbf{PPF-Tracker}. The proposed framework first performs quasi-canonicalization of point clouds in the SE(3) Lie group space, and then models articulated objects using Point Pair Features (PPF) to predict pose voting parameters by leveraging the invariance properties of SE(3). Finally, semantic information of joint axes is incorporated to impose unified kinematic constraints across all parts of the articulated object. PPF-Tracker is systematically evaluated on both synthetic datasets and real-world scenarios, demonstrating strong generalization across diverse and challenging environments. Experimental results highlight the effectiveness and robustness of PPF-Tracker in multi-frame pose tracking of articulated objects. We believe this work can foster advances in robotics, embodied intelligence, and augmented reality. Codes are available at https://github.com/mengxh20/PPFTracker.