The setup of our system. Three Kinects are used to capture different parts of a human body at a close distance without interference. The captured data of a single frame from three sensors is also illustrated.
Abstract
Depth camera such as
Microsoft Kinect, is much cheaper than conventional 3D scanning devices,
and thus it can be acquired for everyday users easily. However, the
depth data captured by Kinect over a certain distance is of extreme low
quality. In this paper, we present a novel scanning system for capturing
3D full human body models by using multiple Kinects. To avoid the
interference phenomena, we use two Kinects to capture the upper part and
lower part of a human body respectively without overlapping region. A
third Kinect is used to capture the middle part of the human body from
the opposite direction. We propose a practical approach for registering
the various body parts of different views under non-rigid deformation.
First, a rough mesh template is constructed and used to deform
successive frames pairwisely. Second, global alignment is performed to
distribute errors in the deformation space, which can solve the loop
closure problem efficiently. Misalignment caused by complex occlusion
can also be handled reasonably by our global alignment algorithm. The
experimental results have shown the efficiency and applicability of our
system. Our system obtains impressive results in a few minutes with low
price devices, thus is practically useful for generating personalized
avatars for everyday users. Our system has been used for 3D human
animation and virtual try on, and can further facilitate a range of
home-oriented virtual reality (VR) applications.
The reconstructed human body with texture using our method.
Different 3D full human models generated using our system. Note that the geometric details such as faces, dresses and hairstyles are well captured in the 3D models.
Realistic virtual try on experience based on the reconstructed model. (Upper) the try on results; (Lower) the corresponding meshes.
Personalized avatar generated by our system. The motion of the human body is driven by a given skeleton motion sequence.
We would like to thank
the anonymous reviewers for their constructive comments. We thank Lei
Yu, Jing Wu, Jingliang Wu, Xiaoyong Sheng, Xiaoguang Han, and Gang Liu
for their help on the experiments. This work was supported jointly by
the National Natural Science Foundation of China (61170318, 61070071,
60970076, 61173124), Doctoral Science Foundation of Hohai University
(XZX/09B005-05) and Microsoft Research Asia.
title = {Scanning 3D Full Human Bodies using Kinects},
author = {Jing Tong and Jin Zhou and Ligang Liu and Zhigeng Pan and Hao Yan}
journal = {IEEE Transactions on Visualization and Computer Graphics (Proceedings of IEEE Virtual Reality)},
volume = {},
number = {},
pages = {to appear},
year = {2012}
}