RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Images

TL;DR

RDPN6D introduces a dense correspondence-based method for 6DoF object pose estimation from RGB-D images, utilizing residual object coordinate regression to improve accuracy, especially under occlusion.

Contribution

The paper presents a novel residual-based dense point-wise network that enhances 6D pose estimation accuracy using RGB-D images, addressing occlusion challenges.

Findings

Outperforms previous methods in occlusion scenarios

Achieves superior accuracy over state-of-the-art techniques

Effective in diverse real-world conditions

Abstract

In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image. Unlike existing methods that either directly predict objects' poses or rely on sparse keypoints for pose recovery, our approach addresses this challenging task using dense correspondence, i.e., we regress the object coordinates for each visible pixel. Our method leverages existing object detection methods. We incorporate a re-projection mechanism to adjust the camera's intrinsic matrix to accommodate cropping in RGB-D images. Moreover, we transform the 3D object coordinates into a residual representation, which can effectively reduce the output space and yield superior performance. We conducted extensive experiments to validate the efficacy of our approach for 6D pose estimation. Our approach outperforms most previous methods, especially in occlusion scenarios, and demonstrates notable improvements over the state-of-the-art methods. Our code is available on https://github.com/AI-Application-and-Integration-Lab/RDPN6D.