Paper Info
Title
Learning Deep Network for Detecting 3D Object Keypoints and 6D Poses
Abstract
The state-of-art 6D object pose detection methods use convolutional neural networks to estimate objects\u0027 6D poses from RGB images. However, they require huge numbers of images with explicit 3D annotations such as 6D poses, 3D bounding boxes and 3D keypoints, either obtained by manual labeling or inferred from synthetic images generated by 3D CAD models. Manual labeling for a large number of images is a laborious task, and we usually do not have the corresponding 3D CAD models of objects in real environment. In this paper, we develop a keypoint-based 6D object pose detection method (and its deep network) called Object Keypoint based POSe Estimation (OK-POSE). OK-POSE employs relative transformation between viewpoints for training. Specifically, we use pairs of images with object annotation and relative transformation information between their viewpoints to automatically discover objects\u0027 3D keypoints which are geometrically and visually consistent. Then, the 6D object pose can be estimated using a keypoint-based geometric reasoning method with a reference viewpoint. The relative transformation information can be easily obtained from any cheap binocular cameras or most smartphone devices, thus greatly lowering the labeling cost. Experiments have demonstrated that OK-POSE achieves acceptable performance compared to methods relying on the object\u0027s 3D CAD model or a great deal of 3D labeling. These results show that our method can be used as a suitable alternative when there are no 3D CAD models or a large number of 3D annotations.
Year
DOI
Venue
2020
10.1109/CVPR42600.2020.01414
CVPR
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
21
6
Name
Order
Citations
PageRank
Wanqing Zhao1157.07
Shaobo Zhang2187.03
Ziyu Guan355338.43
Wei Zhao413415.36
Jinye Peng528440.93
Jianping Fan62677192.33