典型文献
Mask guided diverse face image synthesis
文献摘要：
Recent studies have shown remarkable success in face image generation task.However,existing approaches have limited diversity,quality and controllability in generating results.To address these issues,we propose a novel end-to-end learning framework to generate diverse,realistic and control-lable face images guided by face masks.The face mask provides a good geometric constraint for a face by specifying the size and location of different components of the face,such as eyes,nose and mouse.The framework consists of four com-ponents:style encoder,style decoder,generator and discri-minator.The style encoder generates a style code which represents the style of the result face;the generator translate the input face mask into a real face based on the style code;the style decoder learns to reconstruct the style code from the generated face image;and the discriminator classifies an input face image as real or fake.With the style code,the proposed model can generate different face images matching the input face mask,and by manipulating the face mask,we can finely control the generated face image.We empirically demonstrate the effectiveness of our approach on mask guided face image synthesis task.
文献关键词：
中图分类号：
作者姓名：
Song SUN;Bo ZHAO;Muhammad MATEEN;Xin CHEN;Junhao WEN
作者机构：
School of Big Data & Software Engineering,Chongqing University,Chongqing 401331,China;Department of Computer Science,The University of British Columbia,Vancouve BC V6T 1Z4,Canada;Department of Computer Science,Air University Multan Campus,Multan 60000,Pakistan
文献出处：
引用格式：
[1]Song SUN;Bo ZHAO;Muhammad MATEEN;Xin CHEN;Junhao WEN-.Mask guided diverse face image synthesis)[J].计算机科学前沿,2022(03):66-74
A类：
minator
B类：
Mask,guided,diverse,face,synthesis,Recent,studies,have,shown,remarkable,success,generation,task,However,existing,approaches,limited,diversity,quality,controllability,generating,results,To,address,these,issues,novel,end,learning,framework,realistic,lable,images,by,masks,provides,good,geometric,constraint,specifying,size,location,different,components,such,eyes,nose,mouse,consists,four,style,encoder,decoder,generator,generates,which,represents,translate,input,into,learns,reconstruct,from,generated,discriminator,classifies,fake,With,proposed,model,can,matching,manipulating,finely,We,empirically,demonstrate,effectiveness
AB值：
0.455112
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。
