A wifi vision-based 3D human mesh reconstruction

A wifi vision-based 3D human mesh reconstruction
复制标题

基于wifi视觉的3D人体网格重建

DOI:
10.1145/3495243.3558247
复制
发表时间:
2022
期刊:
Proceedings of the 28th Annual International Conference on Mobile Computing And Networking
影响因子:
--
通讯作者:
Jie Yang
Jie Yang
中科院分区:
--
文献类型:
--
作者:
Yichao Wang;Yili Ren;Yingying Chen;Jie Yang

文献摘要

参考文献

被引文献

相似文献

在这项工作中,我们提出了Wi-Mesh,一个基于WiFi视觉的3D人体网格构建系统。我们的系统利用WiFi的进步来可视化人体的形状和变形,以构建3D网格。特别是,它估计了WiFi信号反射的二维到达角(2D AOA),使WiFi设备能够像我们人类一样“看到”物理环境。然后,它只从物理环境中提取人体图像,并利用深度学习模型将提取的人体数字化为3D网格表示。在不同室内环境下的实验评估表明,Wi-Mesh的平均顶点定位误差为2.58 cm,节点定位误差为2.24 cm。
In this work, we present, Wi-Mesh, a WiFi vision-based 3D human mesh construction system. Our system leverages the advances of WiFi to visualize the shape and deformations of the human body for 3D mesh construction. In particular, it estimates the two-dimensional angle of arrival (2D AoA) of the WiFi signal reflections to enable WiFi devices to "see" the physical environment as we humans do. It then extracts only the images of the human body from the physical environment, and leverages deep learning models to digitize the extracted human body into 3D mesh representation. Experimental evaluation under various indoor environments shows that Wi-Mesh achieves an average vertices location error of 2.58cm and joint position error of 2.24cm.
DOI: 10.1145/3494973
发表时间: 2021
期刊: Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.
影响因子: --
作者:
Yili Ren;Z. Wang;Sheng Tan;Yingying Chen;Jie Yang
通讯作者: Yili Ren;Z. Wang;Sheng Tan;Yingying Chen;Jie Yang