Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation

TL;DR

This paper introduces a novel 3D graph convolution pipeline with a flexible vector-based rotation representation for improved category-level 6D object pose and size estimation from RGB-D images, achieving state-of-the-art results.

Contribution

It proposes a new vector-based rotation representation and a 3D graph convolution autoencoder for robust, category-level 6D pose estimation with enhanced generalization.

Findings

Achieves state-of-the-art performance on category-level pose estimation tasks.

The proposed rotation representation outperforms existing methods.

The pipeline demonstrates strong generalization capabilities.

Abstract

In this paper, we propose a novel 3D graph convolution based pipeline for category-level 6D pose and size estimation from monocular RGB-D images. The proposed method leverages an efficient 3D data augmentation and a novel vector-based decoupled rotation representation. Specifically, we first design an orientation-aware autoencoder with 3D graph convolution for latent feature learning. The learned latent feature is insensitive to point shift and size thanks to the shift and scale-invariance properties of the 3D graph convolution. Then, to efficiently decode the rotation information from the latent feature, we design a novel flexible vector-based decomposable rotation representation that employs two decoders to complementarily access the rotation information. The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task. Finally, we propose a 3D deformation mechanism to increase the generalization ability of the pipeline. Extensive experiments show that the proposed pipeline achieves state-of-the-art performance on category-level tasks. Further, the experiments demonstrate that the proposed rotation representation is more suitable for the pose estimation tasks than other rotation representations.