RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking
arXiv:1910.00694 · doi:10.1109/ICCVW.2019.00568
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/.
arXiv commentThis model is the winning submission for OpenEDS Semantic Segmentation Challenge for Eye images https://research.fb.com/programs/openeds-challenge/. To appear in ICCVW 2019. ("Pre-trained models and source code are available https://bitbucket.org/eye-ush/ritnet/.")
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
- Deep Pictorial Gaze Estimation
- Pupil: An Open Source Platform for Pervasive Eye Tracking and Mobile Gaze-based Interaction
- OpenEDS: Open Eye Dataset
- EyeNet: A Multi-Task Network for Off-Axis Eye Gaze Estimation and User Understanding
Cited by in corpus (18)
- EllSeg: An Ellipse Segmentation Framework for Robust Gaze Tracking
- A High-Level Description and Performance Evaluation of Pupil Invisible
- Exploring Extended Reality with ILLIXR: A New Playground for Architecture Research
- Automatic Gaze Analysis: A Survey of Deep Learning based Approaches
- RIT-Eyes: Rendering of near-eye images for eye-tracking applications
- EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking
- EyeCoD: Eye Tracking System Acceleration via FlatCam-based Algorithm & Accelerator Co-Design
- Privacy-Preserving Eye Videos using Rubber Sheet Model
- Multistream Gaze Estimation with Anatomical Eye Region Isolation by Synthetic to Real Transfer Learning
- Using Deep Learning to Increase Eye-Tracking Robustness, Accuracy, and Precision in Virtual Reality
- BOXR: Body and head motion Optimization framework for eXtended Reality
- MagicEyes: A Large Scale Eye Gaze Estimation Dataset for Mixed Reality
- A3FR: Agile 3D Gaussian Splatting with Incremental Gaze Tracked Foveated Rendering in Virtual Reality
- Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer
- Eye Semantic Segmentation with a Lightweight Model
- Trade-offs in Privacy-Preserving Eye Tracking through Iris Obfuscation: A Benchmarking Study
- - Enhancing the Precision of Eye Tracking using Iris Feature Motion Vectors
- Dataset for eye-tracking tasks