期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 32, 期 8, 页码 5163-5174出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3138129
关键词
Pose estimation; Point cloud compression; Annotations; Feature extraction; Solid modeling; Training; Three-dimensional displays; Object pose estimation; semi-supervised learning; point cloud
资金
- National Natural Science Foundation of China [61733013, 62073245]
The research proposes a semi-supervised pose estimation method using labeled synthetic data and unlabeled real data. It improves network performance through a self-supervised pipeline and feature mapping, and enhances accuracy with an attention-based pose estimation network.
6D object pose estimation is a longstanding computer vision problem. Existing deep learning-based methods have achieved inspiring results in this task. However, large-scale training data with annotations is extremely needed to guarantee these methods' performance, and acquiring real 6D object pose annotations is fairly labor-intensive and time-consuming. To overcome this drawback, we propose a semi-supervised pose estimation method using labeled synthetic data and unlabeled real data. For unlabeled real data, we form a self-supervised pipeline by minimizing the distance between the input point cloud, which is under ground-truth pose, and the model points transformed based on predicted pose. The labeled synthetic data is used to supervise the network to converge correctly. And we utilize a feature mapping to eliminate the domain gap between the real and synthetic features to further enhance the network's performance. Moreover, we propose an attention-based pose estimation network, which can concentrate more on the distinguishing features, thus improving the accuracy of pose estimation. Experiments show that our proposed semi-supervised method is able to achieve good performance without the real annotations and outperforms all other methods relying on synthetic data or self-supervision strategy, indicating that the proposed method is effective.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据