Skip to main content

Deep VOG for gaze estimation

Project description


DeepVOG is a framework for pupil segmentation and gaze estimation based on a fully convolutional neural network.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.


To run DeepVOG, you need to have a Python distribution (we recommend Anaconda) and the following Python packages:



A step by step series of examples that tell you how to get DeepVOG running.

Publication and Citation

If you plan to use this work in your research or product, please cite this repository and our publication pre-print on arXiv.


  • Yiu Yuk Hoi - Implementation and validation
  • Seyed-Ahmad Ahmadi - Research study concept
  • Moustafa Aboulatta - Initial work


This project is licensed under the GNU General Public License v3.0 (GNU GPLv3) License - see the LICENSE file for details


We thank our fellow researchers at the German Center for Vertigo and Balance Disorders for help in acquiring data for training and validation of pupil segmentation and gaze estimation. In particular, we would like to thank Theresa Raiser, Dr. Virginia Flanagin and Prof. Dr. Peter zu Eulenburg.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for deepvog, version 1.0.1.dev4
Filename, size File type Python version Upload date Hashes
Filename, size deepvog-1.0.1.dev4-py3-none-any.whl (35.3 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size deepvog-1.0.1.dev4.tar.gz (20.2 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page