Gaze360: Physically Unconstrained Gaze Estimation in the Wild
Name
1910.10088.pdf
Description
Submitted version
Size
9.2 MB
Format
Adobe PDF
Checksum (MD5)
ceefb315f01cb328c85cf3c969fb414e
Author(s)
Kellnhofer, Petr
Recasens, Adria
Stent, Simon
Matusik, Wojciech
Torralba, Antonio
Date Issued
2019
Journal
Proceedings of the IEEE International Conference on Computer Vision
Publisher
IEEE
Citation
Kellnhofer, Petr, Recasens, Adria, Stent, Simon, Matusik, Wojciech and Torralba, Antonio. 2019. "Gaze360: Physically Unconstrained Gaze Estimation in the Wild." Proceedings of the IEEE International Conference on Computer Vision, 2019-October.
Version
Original manuscript
Abstract
© 2019 IEEE. Understanding where people are looking is an informative social cue. In this work, we present Gaze360, a large-scale remote gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our dataset consists of 238 subjects in indoor and outdoor environments with labelled 3D gaze across a wide range of head poses and distances. It is the largest publicly available dataset of its kind by both subject and variety, made possible by a simple and efficient collection method. Our proposed 3D gaze model extends existing models to include temporal information and to directly output an estimate of gaze uncertainty. We demonstrate the benefits of our model via an ablation study, and show its generalization performance via a cross-dataset evaluation against other recent gaze benchmark datasets. We furthermore propose a simple self-supervised approach to improve cross-dataset domain adaptation. Finally, we demonstrate an application of our model for estimating customer attention in a supermarket setting. Our dataset and models will be made available at http://gaze360.csail.mit.edu.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICCV.2019.00701
