Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild
This work improves gaze estimation for applications like human-computer interaction and assistive technologies, though it appears incremental as it builds on existing appearance-based methods.
The paper tackles the problem of unconstrained remote gaze estimation by addressing its vulnerability to head movement variability, proposing novel end-to-end appearance-based methods that incorporate head-pose representations. The result is a method that outperforms state-of-the-art approaches by a significant margin on multiple datasets, including a new benchmark with rich head-gaze distributions.
Unconstrained remote gaze estimation remains challenging mostly due to its vulnerability to the large variability in head-pose. Prior solutions struggle to maintain reliable accuracy in unconstrained remote gaze tracking. Among them, appearance-based solutions demonstrate tremendous potential in improving gaze accuracy. However, existing works still suffer from head movement and are not robust enough to handle real-world scenarios. Especially most of them study gaze estimation under controlled scenarios where the collected datasets often cover limited ranges of both head-pose and gaze which introduces further bias. In this paper, we propose novel end-to-end appearance-based gaze estimation methods that could more robustly incorporate different levels of head-pose representations into gaze estimation. Our method could generalize to real-world scenarios with low image quality, different lightings and scenarios where direct head-pose information is not available. To better demonstrate the advantage of our methods, we further propose a new benchmark dataset with the most rich distribution of head-gaze combination reflecting real-world scenarios. Extensive evaluations on several public datasets and our own dataset demonstrate that our method consistently outperforms the state-of-the-art by a significant margin.