Egocentric Human Segmentation for Mixed Reality
arXiv:2005.12074
Abstract
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.
Accepted for presentation at EPIC@CVPR2020 workshop
Cited by in corpus (3)
- All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda
- Small Object Detection for Near Real-Time Egocentric Perception in a Manual Assembly Scenario
- Real Time Egocentric Object Segmentation: THU-READ Labeling and Benchmarking Results