Webcam-based Pupil Diameter Prediction Benefits from Upscaling

TL;DR

This paper investigates how different upscaling techniques improve the accuracy of pupil diameter prediction from low-resolution eye images, emphasizing the importance of selecting appropriate methods for psychological and physiological assessments.

Contribution

It systematically evaluates various upscaling methods' effects on pupilometry accuracy, highlighting the significance of upscaling choices in predictive modeling.

Findings

Upscaling improves pupil diameter prediction accuracy.

Models are highly sensitive to the choice of upscaling method.

Advanced super-resolution techniques yield better results.

Abstract

Capturing pupil diameter is essential for assessing psychological and physiological states such as stress levels and cognitive load. However, the low resolution of images in eye datasets often hampers precise measurement. This study evaluates the impact of various upscaling methods, ranging from bicubic interpolation to advanced super-resolution, on pupil diameter predictions. We compare several pre-trained methods, including CodeFormer, GFPGAN, Real-ESRGAN, HAT, and SRResNet. Our findings suggest that pupil diameter prediction models trained on upscaled datasets are highly sensitive to the selected upscaling method and scale. Our results demonstrate that upscaling methods consistently enhance the accuracy of pupil diameter prediction models, highlighting the importance of upscaling in pupilometry. Overall, our work provides valuable insights for selecting upscaling techniques, paving the way for more accurate assessments in psychological and physiological research.