典型文献
NormFuse:Infrared and Visible Image Fusion With Pixel-Adaptive Normalization
文献摘要：
Dear Editor,
This letter presents a normalization mechanism to effectively fuse infrared and visible images in an encoder-decoder network.Source images are decomposed into source-invariant structure and source-specific detail features.Then,the information of detail features is sufficiently incorporated into the structure features using this normal-ization mechanism in the decoder,which generates high-contrast fused images with highlighted targets and abundant texture informa-tion.Qualitative and quantitative experiments on two challenging datasets demonstrate the superiority of our method over current state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
Quan Kong;Huabing Zhou;Yuntao Wu
作者机构：
School of Art and Design and School of Computer Science and Engineering Artificial Intelligence,Wuhan Institute of Technology,Wuhan 430205,China;School of Computer Science and Engineering Artificial Intelligence and Hubei Key Laboratory of Intelligent Robot,Wuhan Institute of Technology,Wuhan 430205,China
文献出处：
引用格式：
[1]Quan Kong;Huabing Zhou;Yuntao Wu-.NormFuse:Infrared and Visible Image Fusion With Pixel-Adaptive Normalization)[J].自动化学报（英文版）,2022(12):2190-2192
A类：
NormFuse
B类：
Infrared,Visible,Image,Fusion,With,Pixel,Adaptive,Normalization,Dear,Editor,
This,letter,presents,normalization,mechanism,effectively,infrared,visible,images,encoder,decoder,network,Source,decomposed,into,source,invariant,structure,specific,detail,features,Then,information,sufficiently,incorporated,using,this,which,generates,contrast,fused,highlighted,targets,abundant,texture,Qualitative,quantitative,experiments,challenging,datasets,demonstrate,superiority,over,current,state,art,methods
AB值：
0.663301
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
