期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 42, 期 8, 页码 1898-1912出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2907951
关键词
Three-dimensional displays; Pose estimation; Solid modeling; Optimization; Feedback loop; Training data; Data models; 3D hand pose estimation; 3D object pose estimation; feedback loop; hand-object manipulation
We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop. The components of this feedback loop are also Deep Networks, optimized using training data. This approach can be generalized to a hand interacting with an object. Therefore, we jointly estimate the 3D pose of the hand and the 3D pose of the object. Our approach performs en-par with state-of-the-art methods for 3D hand pose estimation, and outperforms state-of-the-art methods for joint hand-object pose estimation when using depth images only. Also, our approach is efficient as our implementation runs in real-time on a single GPU.
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