期刊
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
卷 -, 期 -, 页码 2335-2343出版社
IEEE COMPUTER SOC
DOI: 10.1109/ICCV.2019.00242
关键词
-
资金
- Singapore Ministry of Education Academic Research Fund Tier 1
- Helmholtz Association
Hand pose estimation from monocular RGB inputs is a highly challenging task. Many previous works for monocular settings only used RGB information for training despite the availability of corresponding data in other modalities such as depth maps. In this work, we propose to learn a joint latent representation that leverages other modalities as weak labels to improve RGB-based hand pose estimation. By design, our architecture is highly flexible in embedding various diverse modalities such as heat maps, depth maps and point clouds. In particular, we find that encoding and decoding the point cloud of the hand surface can improve the quality of the joint latent representations. Experiments show that with the aid of other modalities during training, our proposed method boosts the accuracy of RGB-based hand pose estimation systems and significantly outperforms state-of-the-art on two public benchmarks.
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