Person-Independent 3D Gaze Estimation Using Face Frontalization
Abstract
Person-independent and pose-invariant estimation of eye-gaze is important for situation analysis and for automated video annotation. We propose a fast cascade regression based method that first estimates the location of a dense set of markers and their visibility, then reconstructs face shape by fitting a part-based 3D model. Next, the reconstructed 3D shape is used to estimate a canonical view of the eyes for 3D gaze estimation. The model operates in a feature space that naturally encodes local ordinal properties of pixel intensities leading to photometric invariant estimation of gaze. To evaluate the algorithm in comparison with alternative approaches, three publicly-available databases were used, Boston University Head Tracking, Multi-View Gaze and CAVE Gaze datasets. Precision for head pose and gaze averaged 4 degrees or less for pitch, yaw, and roll. The algorithm outperformed alternative methods in both datasets.
Cite
Text
Jeni and Cohn. "Person-Independent 3D Gaze Estimation Using Face Frontalization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016. doi:10.1109/CVPRW.2016.104Markdown
[Jeni and Cohn. "Person-Independent 3D Gaze Estimation Using Face Frontalization." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016.](https://mlanthology.org/cvprw/2016/jeni2016cvprw-personindependent/) doi:10.1109/CVPRW.2016.104BibTeX
@inproceedings{jeni2016cvprw-personindependent,
title = {{Person-Independent 3D Gaze Estimation Using Face Frontalization}},
author = {Jeni, László A. and Cohn, Jeffrey F.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2016},
pages = {792-800},
doi = {10.1109/CVPRW.2016.104},
url = {https://mlanthology.org/cvprw/2016/jeni2016cvprw-personindependent/}
}