PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation

TL;DR

This paper introduces PR-GCN, a deep learning framework that enhances 6D pose estimation from RGB-D data by refining point clouds and effectively integrating multi-modal information, achieving state-of-the-art results.

Contribution

The paper presents a novel unified approach combining point cloud refinement and multi-modal graph convolutional networks for improved 6D pose estimation.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates effective refinement of 3D point clouds.

Shows generalization of modules to other frameworks.

Abstract

RGB-D based 6D pose estimation has recently achieved remarkable progress, but still suffers from two major limitations: (1) ineffective representation of depth data and (2) insufficient integration of different modalities. This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way. It first introduces the Point Refinement Network (PRN) to polish 3D point clouds, recovering missing parts with noise removed. Subsequently, the Multi-Modal Fusion Graph Convolutional Network (MMF-GCN) is presented to strengthen RGB-D combination, which captures geometry-aware inter-modality correlation through local information propagation in the graph convolutional network. Extensive experiments are conducted on three widely used benchmarks, and state-of-the-art performance is reached. Besides, it is also shown that the proposed PRN and MMF-GCN modules are well generalized to other frameworks.