HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images

TL;DR

HAZE-Net is a novel deep learning model that enhances low-resolution face images and accurately estimates gaze direction by focusing on high-frequency features and structural face information.

Contribution

This paper introduces HAZE-Net, a high-frequency attentive super-resolution network specifically designed for accurate gaze estimation in very low-resolution face images.

Findings

Robust gaze estimation at 28x28 pixel resolution.

Effective enhancement of eye features via high-frequency attention.

Improved performance over existing methods in low-resolution scenarios.

Abstract

Although gaze estimation methods have been developed with deep learning techniques, there has been no such approach as aim to attain accurate performance in low-resolution face images with a pixel width of 50 pixels or less. To solve a limitation under the challenging low-resolution conditions, we propose a high-frequency attentive super-resolved gaze estimation network, i.e., HAZE-Net. Our network improves the resolution of the input image and enhances the eye features and those boundaries via a proposed super-resolution module based on a high-frequency attention block. In addition, our gaze estimation module utilizes high-frequency components of the eye as well as the global appearance map. We also utilize the structural location information of faces to approximate head pose. The experimental results indicate that the proposed method exhibits robust gaze estimation performance even in low-resolution face images with 28x28 pixels. The source code of this work is available at https://github.com/dbseorms16/HAZE_Net/.