Real Time Egocentric Object Segmentation: THU-READ Labeling and Benchmarking Results
This work addresses the problem of limited data for egocentric object segmentation, which is crucial for Mixed Reality applications, but it is incremental as it builds on existing datasets and methods.
The paper tackles the lack of datasets for egocentric object segmentation by providing semantic-wise labeling for 2124 images from the THU-READ Dataset and reports benchmarking results using Thundernet, achieving real-time performance suitable for Mixed Reality applications.
Egocentric segmentation has attracted recent interest in the computer vision community due to their potential in Mixed Reality (MR) applications. While most previous works have been focused on segmenting egocentric human body parts (mainly hands), little attention has been given to egocentric objects. Due to the lack of datasets of pixel-wise annotations of egocentric objects, in this paper we contribute with a semantic-wise labeling of a subset of 2124 images from the RGB-D THU-READ Dataset. We also report benchmarking results using Thundernet, a real-time semantic segmentation network, that could allow future integration with end-to-end MR applications.