Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism

In recent years, convolutional neural network in Single image super-resolution field show good results. Deep networks can establish complex mapping between low-resolution and high-resolution images, making the reconstructed images quality a great progress over traditional methods. In order to be abl...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenglin Yu, Hailong Pei
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9395111/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850098438221332480
author Chenglin Yu
Hailong Pei
author_facet Chenglin Yu
Hailong Pei
author_sort Chenglin Yu
collection DOAJ
description In recent years, convolutional neural network in Single image super-resolution field show good results. Deep networks can establish complex mapping between low-resolution and high-resolution images, making the reconstructed images quality a great progress over traditional methods. In order to be able to generate face images with rich texture details, the algorithm proposed in this paper captures implicit weight information in channel and space domains through dual attention modules, so as to allocate computing resources more effectively and speed up the network convergence. Fusion of global features through residual connections in this network not only focus on learning the high frequency information of images that has been lost, but also accelerate the network convergence through effective feature supervision. In order to alleviate the defects of MAE loss function, a special Huber loss function is introduced in the algorithm. The experimental results on benchmark show that the proposed algorithm has a significant improvement in image reconstruction accuracy compared with existed SISR methods.
format Article
id doaj-art-ec746b2acb454d58ad07746f994fee01
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ec746b2acb454d58ad07746f994fee012025-08-20T02:40:43ZengIEEEIEEE Access2169-35362025-01-011312125012126010.1109/ACCESS.2021.30708989395111Super-Resolution Reconstruction Method of Face Image Based on Attention MechanismChenglin Yu0https://orcid.org/0000-0002-4413-3142Hailong Pei1https://orcid.org/0000-0003-3295-4557Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, South China University of Technology, Guangzhou, ChinaKey Laboratory of Autonomous Systems and Networked Control, Ministry of Education, Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong, School of Automation Science and Engineering, South China University of Technology, Guangzhou, ChinaIn recent years, convolutional neural network in Single image super-resolution field show good results. Deep networks can establish complex mapping between low-resolution and high-resolution images, making the reconstructed images quality a great progress over traditional methods. In order to be able to generate face images with rich texture details, the algorithm proposed in this paper captures implicit weight information in channel and space domains through dual attention modules, so as to allocate computing resources more effectively and speed up the network convergence. Fusion of global features through residual connections in this network not only focus on learning the high frequency information of images that has been lost, but also accelerate the network convergence through effective feature supervision. In order to alleviate the defects of MAE loss function, a special Huber loss function is introduced in the algorithm. The experimental results on benchmark show that the proposed algorithm has a significant improvement in image reconstruction accuracy compared with existed SISR methods.https://ieeexplore.ieee.org/document/9395111/Super-resolutionfeature supervisionchannel attentionspatial attention
spellingShingle Chenglin Yu
Hailong Pei
Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism
IEEE Access
Super-resolution
feature supervision
channel attention
spatial attention
title Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism
title_full Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism
title_fullStr Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism
title_full_unstemmed Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism
title_short Super-Resolution Reconstruction Method of Face Image Based on Attention Mechanism
title_sort super resolution reconstruction method of face image based on attention mechanism
topic Super-resolution
feature supervision
channel attention
spatial attention
url https://ieeexplore.ieee.org/document/9395111/
work_keys_str_mv AT chenglinyu superresolutionreconstructionmethodoffaceimagebasedonattentionmechanism
AT hailongpei superresolutionreconstructionmethodoffaceimagebasedonattentionmechanism