arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.04071cs.CV
收藏

DeepFuse:一种基于IMU的多视点图像实时的三维人体姿态估计网络

DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image

The Chinese University of Hong Kong(香港中文大学)

Fuyang Huang, Ailing Zeng, Minhao Liu, Qiuxia Lai, Qiang Xu

摘要:

本文提出了一种两级全三维网络(\textbf{DeepFuse}),通过深度融合体戴式惯性测量单元(IMU)数据和多视角图像来估计三维空间中的人体位姿。第一阶段是设计用于纯视觉估计。为了保持多视图输入的数据连续性,视觉阶段使用多通道体积作为数据表示,并使用3D soft-argmax作为激活层。第二个是IMU细化阶段,该阶段引入IMU骨骼层以在数据级更早地融合IMU和视觉数据。在不需要先验给定骨架模型的情况下,我们可以在协议1下在TotalCapture数据集上实现$28.9$ mm的平均联合误差,在Human3.6M数据集上实现$13.4$ mm的平均联合误差,从而大幅改善了SOTA结果。最后,我们讨论了一个完整的三维网络的有效性,三维姿态估计实验,这可能有利于未来的研究。

英文摘要:

In this paper, we propose a two-stage fully 3D network, namely \textbf{DeepFuse}, to estimate human pose in 3D space by fusing body-worn Inertial Measurement Unit (IMU) data and multi-view images deeply. The first stage is designed for pure vision estimation. To preserve data primitiveness of multi-view inputs, the vision stage uses multi-channel volume as data representation and 3D soft-argmax as activation layer. The second one is the IMU refinement stage which introduces an IMU-bone layer to fuse the IMU and vision data earlier at data level. without requiring a given skeleton model a priori, we can achieve a mean joint error of $28.9$mm on TotalCapture dataset and $13.4$mm on Human3.6M dataset under protocol 1, improving the SOTA result by a large margin. Finally, we discuss the effectiveness of a fully 3D network for 3D pose estimation experimentally which may benefit future research.

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。

↑