A Differential Approach for Gaze Estimation
This addresses the problem of subject-dependent biases in gaze estimation for applications like human-computer interaction, offering a novel method to improve accuracy without extensive calibration.
The paper tackles the problem of limited accuracy and high variance in non-invasive gaze estimation by introducing a differential convolutional neural network that predicts gaze differences between two eye images of the same subject, reducing annoyance factors like alignment and illumination. Experiments on three public datasets show it consistently outperforms state-of-the-art methods, even with only one calibration sample.
Non-invasive gaze estimation methods usually regress gaze directions directly from a single face or eye image. However, due to important variabilities in eye shapes and inner eye structures amongst individuals, universal models obtain limited accuracies and their output usually exhibit high variance as well as biases which are subject dependent. Therefore, increasing accuracy is usually done through calibration, allowing gaze predictions for a subject to be mapped to his/her actual gaze. In this paper, we introduce a novel image differential method for gaze estimation. We propose to directly train a differential convolutional neural network to predict the gaze differences between two eye input images of the same subject. Then, given a set of subject specific calibration images, we can use the inferred differences to predict the gaze direction of a novel eye sample. The assumption is that by allowing the comparison between two eye images, annoyance factors (alignment, eyelid closing, illumination perturbations) which usually plague single image prediction methods can be much reduced, allowing better prediction altogether. Experiments on 3 public datasets validate our approach which constantly outperforms state-of-the-art methods even when using only one calibration sample or when the latter methods are followed by subject specific gaze adaptation.