计算机与数字工程2024，Vol.52Issue(10)：3065-3071,7.DOI:10.3969/j.issn.1672-9722.2024.10.037
基于高效注意力机制的人脸超分辨网络
Face Super-Resolution Network Based on Efficient Attention Mechanisms
摘要
Abstract
Currently,deep learning methods based on facial priors have been able to better recover the details of degraded face images.However,these methods still have some shortcomings.On the one hand,multi-task joint training requires additional prior labeling on the dataset,and the introduction of the priors will significantly increase the computational cots of the network.On the other hand,most methods only use convolutional neural networks(CNN),the limited perceptive field of CNN will reduce the in-tegrity and accuracy of the reconstructed facial images.To address these problems,a face super-resolution network based on effi-cient attention mechanisms is proposed.The network combines CNN with several attention mechanisms such as Transformer.It can effectively recover the global structure and local texture details of a face without the aid of any facial priors.Extensive experiments on various datasets show the effectiveness of the proposed network.关键词
人脸超分辨率/Transformer/卷积神经网络/注意力机制Key words
face super-resolution/Transformer/convolutional neural network/attention mechanism分类
信息技术与安全科学引用本文复制引用
许子祥,豆锐,李佳雯,高广谓..基于高效注意力机制的人脸超分辨网络[J].计算机与数字工程,2024,52(10):3065-3071,7.基金项目
国家自然科学基金项目(编号:61972212) （编号:61972212）
江苏省自然科学基金项目(编号:BK20190089) （编号:BK20190089）
江苏省"六大人才高峰"项目(编号:RJFW-011) （编号:RJFW-011）
苏州大学江苏省计算机信息处理技术重点实验室开放课题(编号:KJS1840)资助. （编号:KJS1840）
