Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings

TL;DR

This paper introduces a learning-based eye landmark localization method trained on synthetic data that improves gaze estimation accuracy in unconstrained real-world settings, outperforming existing methods.

Contribution

A novel synthetic-data trained landmark localization approach enhances gaze estimation in real-world scenarios, bridging the gap between model-based and appearance-based methods.

Findings

Exceeds state-of-the-art in iris localization and eye shape registration on real images.

Improves person-independent and personalized gaze estimation accuracy.

Outperforms existing model-fitting and appearance-based methods.

Abstract

Conventional feature-based and model-based gaze estimation methods have proven to perform well in settings with controlled illumination and specialized cameras. In unconstrained real-world settings, however, such methods are surpassed by recent appearance-based methods due to difficulties in modeling factors such as illumination changes and other visual artifacts. We present a novel learning-based method for eye region landmark localization that enables conventional methods to be competitive to latest appearance-based methods. Despite having been trained exclusively on synthetic data, our method exceeds the state of the art for iris localization and eye shape registration on real-world imagery. We then use the detected landmarks as input to iterative model-fitting and lightweight learning-based gaze estimation methods. Our approach outperforms existing model-fitting and appearance-based methods in the context of person-independent and personalized gaze estimation.