top of page

​Improving Gaze Reconstruction Accuracy in Generated Faces

This project investigated the effects of adding multiple loss terms to the optimization functions of a face swapping model.  We found that both an image reconstruction metric based on the eyes and a metric using difference in gaze angles derived by a pretrained expert model both increased the accuracy of gaze representation in generated faces.

Funding source(s):

  1. NIH R21 “Protecting the privacy of the child through facial identity removal in recorded behavioral observation sessions” (2020-2022)

Publications

Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms

Wilson, Ethan and Shic, Frederick and Joerg, Sophie and Jain, Eakta.  Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms.  Computers and Graphics Journal Special Issue: Eye Gaze Visualization, Interaction, Synthesis, and Analysis (2024).

Resources:

 

@article{wilson_uncanneyeness_2024,
author = {Ethan Wilson and Frederick Shic and Sophie Jörg and Eakta Jain},
title = {Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms},
year = {2024},
journal = {Computers & Graphics},
doi = {https://doi.org/10.1016/j.cag.2024.103888},
}

gaze_constraints_teaser_figure.png

Introducing Explicit Gaze Constraints to Face Swapping

Wilson, Ethan and Shic, Frederick and Jain, Eakta.  Introducing Explicit Gaze Constraints to Face Swapping.  ACM Symposium on Eye Tracking Research & Applications (ETRA).  (2023) (in press)

Resources:

  • Paper (coming soon)

  • Bibtex:

 

@inproceedings{wilson_gazeconstraints_2023,

title={Introducing Explicit Gaze Constraints to Face Swapping},

author={Wilson, Ethan and Shic, Frederick and Jain, Eakta},

booktitle={2023 Symposium on Eye Tracking Research and Applications},

year={2023}

gaze_constraints_teaser_figure.png
bottom of page