GazeBall: leveraging natural gaze behavior for continuous re-calibration in gameplay

Eye tracking offers opportunities to extend conventional game control with gaze input for multimodal game interaction. Gaze, however, has been found challenging to use as it requires re-calibration over time and for different users, in order to maintain an accurate input. In this work, we propose to leverage the natural gaze behavior that users exhibit during gameplay for implicit and continuous re-calibration. We demonstrate this with GazeBall, continually calibrating players' gaze based on their natural ocular pursuit of the game's ball movement. Re-calibration enables the extension of the game with a gaze-based 'power-up'. In the evaluation of GazeBall, we show that our approach is effective in maintaining highly accurate gaze input over time, while re-calibration remains transparent to the player.