Gaze Estimation Approach Using Deep Differential Residual Network

TL;DR

This paper introduces DRNet, a deep differential residual network that leverages difference information of eye images with a new loss function, significantly improving gaze estimation accuracy and robustness over existing methods.

Contribution

The paper proposes a novel differential residual model with a specialized loss function to enhance gaze estimation accuracy using eye difference information.

Findings

DRNet achieves lower angular error than state-of-the-art methods.

DRNet demonstrates high robustness to noisy images.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Gaze estimation, which is a method to determine where a person is looking at given the person's full face, is a valuable clue for understanding human intention. Similarly to other domains of computer vision, deep learning (DL) methods have gained recognition in the gaze estimation domain. However, there are still gaze calibration problems in the gaze estimation domain, thus preventing existing methods from further improving the performances. An effective solution is to directly predict the difference information of two human eyes, such as the differential network (Diff-Nn). However, this solution results in a loss of accuracy when using only one inference image. We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images. We treat the difference information as auxiliary information. We assess the proposed model (DRNet) mainly using two public datasets (1) MpiiGaze and (2) Eyediap. Considering only the eye features, DRNet outperforms the state-of-the-art gaze estimation methods with $angular-error$ of 4.57 and 6.14 using MpiiGaze and Eyediap datasets, respectively. Furthermore, the experimental results also demonstrate that DRNet is extremely robust to noise images.