KGpose: Keypoint-Graph Driven End-to-End Multi-Object 6D Pose Estimation via Point-Wise Pose Voting

TL;DR

KGpose is an innovative end-to-end framework that estimates multiple objects' 6D poses by combining keypoint graphs and point-wise voting, improving efficiency and accuracy in complex scenes.

Contribution

It introduces a novel keypoint-graph representation and integrates it with point-wise pose voting for multi-object 6D pose estimation.

Findings

Achieves competitive results on benchmark datasets.

Enables multi-object pose estimation without extra localization steps.

Provides a unified approach for geometric understanding in scenes.

Abstract

This letter presents KGpose, a novel end-to-end framework for 6D pose estimation of multiple objects. Our approach combines keypoint-based method with learnable pose regression through `keypoint-graph', which is a graph representation of the keypoints. KGpose first estimates 3D keypoints for each object using an attentional multi-modal feature fusion of RGB and point cloud features. These keypoints are estimated from each point of point cloud and converted into a graph representation. The network directly regresses 6D pose parameters for each point through a sequence of keypoint-graph embedding and local graph embedding which are designed with graph convolutions, followed by rotation and translation heads. The final pose for each object is selected from the candidates of point-wise predictions. The method achieves competitive results on the benchmark dataset, demonstrating the effectiveness of our model. KGpose enables multi-object pose estimation without requiring an extra localization step, offering a unified and efficient solution for understanding geometric contexts in complex scenes for robotic applications.