EyeLis Dataset V1

Dataset Description

Dataset containing eye images annotated with 3D head orientation and gaze direction vectors.

Contents

• 9 participants (P1 to P9)
• For each image (.png):
  • Corresponding JSON file containing:

    Head_vector: 3D head orientation
    Pupil_vector: 3D gaze direction
                            

Folder Structure

EyeLis/
├── P1/
│   ├── Eye1.png
│   ├── Eye1.json
│   ├── ...
├── P2/
├── ...
└── P9/
        

Citation

If you use this dataset in your research, please cite:

Bendimered, A.; Iguernaissi, R.; Nawaf, M. M.; Cherif, R.; Dubuisson, S.; Merad, D.
Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation in Real-World Conditions.
Sensors 2025, 1, 0. - Soon...
        

Request Access