# Egocentric Human Segmentation for Mixed Reality

Source: [Egocentric Human Segmentation for Mixed Reality](<https://www.sota2.com/research/paper/68fa67aa1e209131cea179b7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:19:06.029Z

Authors: Andrija Gajic, Ester Gonzalez-Sosa, Diego Gonzalez-Morin, Marcos Escudero-Vi\\~nolo, Alvaro Villegas

Published: 2020-05-25T12:34:47.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2005.12074>)

[PDF](<https://arxiv.org/pdf/2005.12074.pdf>)