典型文献
DIUN:Deeper Inception U-Network for Recovering Partial Pixelated Images
文献摘要：
In our daily life,it is nothing strange to see pixelated images that are spoiled artificially to hide certain information for protecting privacy or pixelated deliberately to cover up bad behaviors even crimes.To prevent these phenomena and recover the true information from pixelated images,it is meaningful to research an effective reconstruction method for recovering pixelated images.This paper aims at recovering the artificial partial pixelated images via deep learning(DL).To abstract more abundant features and enhance the repair ability of DL model,we propose a new DL structure,called deeper inception U-Net,to act as the generator of a generative adversarial network.We combine the feature loss with structural similarity index measure loss as the context loss to minimize the distance between feature maps of clear images and the generated images,which helps to improve the quality of repair images.After obtaining inception features,we use fusion layer to adaptively learn features in each inception block.To evaluate the performance of our model,we introduce a new home dataset that contains 10174 clear home images with corresponding pixelated images.A series of experiments show that our model has ability to rebuild pixelated images.
文献关键词：
中图分类号：
作者姓名：
Hufei YU;Shiwen HE;Min ZHANG;Wenwu XIE;Yan TANG
作者机构：
School of Computer Science and Engineering,Central South University,Changsha 410083,China;National Mobile Communications Research Laboratory,Southeast University,Nanjing 210096,China;Purple Mountain Laboratories,Nanjing 210096,China;Hunan Post and Telecommunication College,Changsha 410083,China;Department of Information Science and Engineering,College of Hunan Institute of Science and Technology,Yueyang 414006,China
文献出处：
引用格式：
[1]Hufei YU;Shiwen HE;Min ZHANG;Wenwu XIE;Yan TANG-.DIUN:Deeper Inception U-Network for Recovering Partial Pixelated Images)[J].系统科学与信息学报（英文版）,2022(02):193-202
A类：
DIUN,Recovering,Pixelated,pixelated
B类：
Deeper,Inception,Network,Partial,Images,our,daily,life,nothing,strange,see,images,that,are,spoiled,artificially,hide,certain,information,protecting,privacy,deliberately,up,bad,behaviors,crimes,To,prevent,these,phenomena,true,from,meaningful,research,effective,reconstruction,method,recovering,This,paper,aims,partial,via,learning,DL,abstract,more,abundant,features,enhance,repair,ability,model,propose,new,structure,called,deeper,inception,generator,generative,adversarial,network,We,combine,loss,structural,similarity,measure,context,minimize,distance,between,maps,clear,generated,which,helps,improve,quality,After,obtaining,use,fusion,layer,adaptively,each,block,evaluate,performance,introduce,home,dataset,contains,corresponding,series,experiments,show,has,rebuild
AB值：
0.542349
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。
