paper-with-me

Papers

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

2022-09-21 · Jun-Seok Yun, Youngju Na, Hee Hyeon Kim, Hyung-Il Kim, Seok Bong Yoo

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/.

📄 PDF Abstract BibTeX arXiv:2209.10167

Code (1)

dbseorms16/haze_net 공식 구현 pytorch

Tasks

Gaze EstimationSuper-Resolution

Similar Papers 제목 키워드 기반

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

2019-02-12 · Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta 외

The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are remarkable demonstrations of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively inc…

Game of Go

Efficient Dual-domain Image Dehazing with Haze Prior Perception

2025-07-15 · Lirong Zheng, Yanshan Li, Rui Yu, Kaihao Zhang arxiv

Transformers offer strong global modeling for single-image dehazing but come with high computational costs. Most methods rely on spatial features to capture long-range dependencies, making them less effective under compl…

Image Dehazing

A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint

2024-03-27 · CVPR 2024 1 · Xiaofeng Cong, Jie Gui, Jing Zhang, JunMing Hou 외

Existing research based on deep learning has extensively explored the problem of daytime image dehazing. However, few studies have considered the characteristics of nighttime hazy scenes. There are two distinctions betwe…

Image DehazingPseudo Label

DADFNet: Dual Attention and Dual Frequency-Guided Dehazing Network for Video-Empowered Intelligent Transportation

2023-04-19 · Yu Guo, Ryan Wen Liu, Jiangtian Nie, Lingjuan Lyu 외

Visual surveillance technology is an indispensable functional component of advanced traffic management systems. It has been applied to perform traffic supervision tasks, such as object detection, tracking and recognition…

GPUManagementobject-detectionObject Detection

SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing

2025-04-07 · Scientific Reports 2025 4 · Qingjun Niu, Kun Wu, Jialu Zhang, Zhenqi Han, Lizhuang Liu

Single-image dehazing technology plays a significant role in video surveillance and intelligent transportation. However, existing dehazing methods using vanilla convolution only extract features in the temporal domai…

Image DehazingSingle Image Dehazing