GazeTrack: High-Precision Eye Tracking Based on Regularization and Spatial Computing
This work addresses the need for high-precision eye tracking in virtual and augmented reality applications, representing an incremental improvement with novel techniques.
The paper tackled the problem of insufficient gaze accuracy for spatial computing by introducing a new benchmark dataset and methods, achieving reduced gaze angle error with lower computational complexity.
Eye tracking has become increasingly important in virtual and augmented reality applications; however, the current gaze accuracy falls short of meeting the requirements for spatial computing. We designed a gaze collection framework and utilized high-precision equipment to gather the first precise benchmark dataset, GazeTrack, encompassing diverse ethnicities, ages, and visual acuity conditions for pupil localization and gaze tracking. We propose a novel shape error regularization method to constrain pupil ellipse fitting and train on open-source datasets, enhancing semantic segmentation and pupil position prediction accuracy. Additionally, we invent a novel coordinate transformation method similar to paper unfolding to accurately predict gaze vectors on the GazeTrack dataset. Finally, we built a gaze vector generation model that achieves reduced gaze angle error with lower computational complexity compared to other methods.