Light-weight Head Pose Invariant Gaze Tracking
This addresses the challenge of unconstrained remote gaze tracking for applications like human-computer interaction, though it is incremental as it builds on existing CNN methods.
The paper tackled the problem of improving gaze tracking robustness to variable head pose using a novel branched CNN architecture, achieving competitive accuracy with a ten times faster network compared to the state-of-the-art.
Unconstrained remote gaze tracking using off-the-shelf cameras is a challenging problem. Recently, promising algorithms for appearance-based gaze estimation using convolutional neural networks (CNN) have been proposed. Improving their robustness to various confounding factors including variable head pose, subject identity, illumination and image quality remain open problems. In this work, we study the effect of variable head pose on machine learning regressors trained to estimate gaze direction. We propose a novel branched CNN architecture that improves the robustness of gaze classifiers to variable head pose, without increasing computational cost. We also present various procedures to effectively train our gaze network including transfer learning from the more closely related task of object viewpoint estimation and from a large high-fidelity synthetic gaze dataset, which enable our ten times faster gaze network to achieve competitive accuracy to its current state-of-the-art direct competitor.