A Head Pose-free Approach for Appearance-based Gaze Estimation

  • Lu F
  • Okabe T
  • Sugano Y
 et al. 
  • 51

    Readers

    Mendeley users who have this article in their library.
  • 45

    Citations

    Citations of this article.

Abstract

To infer human gaze from eye appearance, various methods have been proposed. However, most of them assume a fixed head pose because allowing free head motion adds 6 degrees of freedom to the problem and requires a prohibitively large number of training samples. In this paper, we aim at solving the appearance-based gaze estimation problem under free head motion without significantly increasing the cost of training. The idea is to decompose the problem into subproblems, including initial estimation under fixed head pose and subsequent compensations for estimation biases caused by head rotation and eye appearance distortion. Then each subproblem is solved by either learning-based method or geometric-based calculation. Specifically, the gaze estimation bias caused by eye appearance distortion is learnt effectively from a 5-seconds video clip. Extensive experiments were conducted to verify the effectiveness of the proposed approach.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Feng Lu

  • Takahiro Okabe

  • Yusuke Sugano

  • Yoichi Sato

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free