arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2002.02033cs.CV
收藏

基于旋转不变混合图模型网络的二维手势估计

Rotation-invariant Mixed Graphical Model Network for 2D Hand Pose Estimation

University of California, Irvine(加州大学欧文分校);Tencent Hippocrates Research Lab(腾讯希波克拉底研究实验室)

Deying Kong, Haoyu Ma, Yifei Chen, Xiaohui Xie

摘要:

在本文中,我们提出了一个新的架构命名为旋转不变的混合图形模型网络(R-MGMN),以解决从单目RGB图像的二维手势估计的问题。通过整合旋转网络,R-MGMN是不变的图像中的手的旋转。它还有一个图形模型池,可以根据输入图像选择图形模型的组合。分别对每个图形模型进行置信度传播,生成一组边缘分布,作为手部关键点位置的置信度图。通过将这些置信图聚合在一起来获得最终置信图。我们在两个公共手部姿势数据集上评估R-MGMN。实验结果表明,我们的模型优于国家的最先进的算法,这是广泛使用的二维手势估计的显着保证金。

英文摘要:

In this paper, we propose a new architecture named Rotation-invariant Mixed Graphical Model Network (R-MGMN) to solve the problem of 2D hand pose estimation from a monocular RGB image. By integrating a rotation net, the R-MGMN is invariant to rotations of the hand in the image. It also has a pool of graphical models, from which a combination of graphical models could be selected, conditioning on the input image. Belief propagation is performed on each graphical model separately, generating a set of marginal distributions, which are taken as the confidence maps of hand keypoint positions. Final confidence maps are obtained by aggregating these confidence maps together. We evaluate the R-MGMN on two public hand pose datasets. Experiment results show our model outperforms the state-of-the-art algorithm which is widely used in 2D hand pose estimation by a noticeable margin.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑