RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking

TL;DR

RITnet is a lightweight deep neural network combining U-Net and DenseNet, achieving high accuracy and real-time performance in eye segmentation for gaze tracking applications.

Contribution

The paper introduces RITnet, a compact and efficient neural network that enables real-time eye segmentation with high accuracy, suitable for gaze tracking.

Findings

Achieves 95.3% accuracy on OpenEDS dataset

Runs at over 300Hz on a GTX 1080 Ti

Model size under 1 MB

Abstract

Accurate eye segmentation can improve eye-gaze estimation and support interactive computing based on visual attention; however, existing eye segmentation methods suffer from issues such as person-dependent accuracy, lack of robustness, and an inability to be run in real-time. Here, we present the RITnet model, which is a deep neural network that combines U-Net and DenseNet. RITnet is under 1 MB and achieves 95.3\% accuracy on the 2019 OpenEDS Semantic Segmentation challenge. Using a GeForce GTX 1080 Ti, RITnet tracks at $>$ 300Hz, enabling real-time gaze tracking applications. Pre-trained models and source code are available https://bitbucket.org/eye-ush/ritnet/.