Effect Of Personalized Calibration On Gaze Estimation Using Deep-Learning

TL;DR

This paper investigates how personalized calibration improves deep learning-based gaze estimation in real-world scenarios, demonstrating that calibration significantly enhances accuracy when the model encounters unfamiliar individuals.

Contribution

The study introduces a calibration mechanism for deep learning gaze estimation models and evaluates its effectiveness using the MPIIGaze dataset, providing insights into real-world application performance.

Findings

Calibration improves gaze estimation accuracy in the wild.

Deep learning models perform better with personalized calibration.

Evaluation on MPIIGaze shows significant performance gains.

Abstract

With the increase in computation power and the development of new state-of-the-art deep learning algorithms, appearance-based gaze estimation is becoming more and more popular. It is believed to work well with curated laboratory data sets, however it faces several challenges when deployed in real world scenario. One such challenge is to estimate the gaze of a person about which the Deep Learning model trained for gaze estimation has no knowledge about. To analyse the performance in such scenarios we have tried to simulate a calibration mechanism. In this work we use the MPIIGaze data set. We trained a multi modal convolutional neural network and analysed its performance with and without calibration and this evaluation provides clear insights on how calibration improved the performance of the Deep Learning model in estimating gaze in the wild.