RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Images
Journal
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Part Of
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Start Page
5251
End Page
5260
ISBN (of the container)
979-835036547-4
Date Issued
2024-06-17
Author(s)
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.
Event(s)
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW
Publisher
IEEE
Type
conference paper