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 2005.12074cs.CV
收藏

基于自我中心的混合现实人体分割

Egocentric Human Segmentation for Mixed Reality

Universidad Autonoma de Madrid(马德里自治大学);Nokia Bell-Labs(诺基亚贝尔实验室)

Andrija Gajic, Ester Gonzalez-Sosa, Diego Gonzalez-Morin, Marcos Escudero-Viñolo, Alvaro Villegas

摘要:

本文的目标是利用语义分割网络从以自我为中心的视频中分割出人体部位。我们的贡献是双重的:i)我们创建了一个半合成数据集,由超过15,000张真实图像和以自我为中心的人体部位的相关像素标签组成,例如包含不同人口统计因素的手臂或腿; ii)基于ThunderNet架构,我们实现了一种深度学习语义分割算法,该算法能够执行超过实时要求(720 x 720图像为16 ms)。相信该方法将增强虚拟环境的临场感,并将构成一个更真实的解决方案,以标准的虚拟化身。

英文摘要:

The objective of this work is to segment human body parts from egocentric video using semantic segmentation networks. Our contribution is two-fold: i) we create a semi-synthetic dataset composed of more than 15, 000 realistic images and associated pixel-wise labels of egocentric human body parts, such as arms or legs including different demographic factors; ii) building upon the ThunderNet architecture, we implement a deep learning semantic segmentation algorithm that is able to perform beyond real-time requirements (16 ms for 720 x 720 images). It is believed that this method will enhance sense of presence of Virtual Environments and will constitute a more realistic solution to the standard virtual avatars.

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。

↑