典型文献
High fidelity virtual try-on network via semantic adaptation and distributed componentization
文献摘要：
Image-based virtual try-on systems have significant commercial value in online garment shopping.However,prior methods fail to appropriately handle details,so are defective in maintaining the original appearance of organizational items including arms,the neck,and in-shop garments.We propose a novel high fidelity virtual try-on network to generate realistic results.Specifically,a distributed pipeline is used for simultaneous generation of organizational items.First,the in-shop garment is warped using thin plate splines(TPS)to give a coarse shape reference,and then a corresponding target semantic map is generated,which can adaptively respond to the distribution of different items triggered by different garments.Second,organizational items are componentized separately using our novel semantic map-based image adjustment network(SMIAN)to avoid interference between body parts.Finally,all components are integrated to generate the overall result by SMIAN.A priori dual-modal information is incorporated in the tail layers of SMIAN to improve the convergence rate of the network.Experiments demonstrate that the proposed method can retain better details of condition information than current methods.Our method achieves convincing quantitative and qualitative results on existing benchmark datasets.
文献关键词：
中图分类号：
作者姓名：
Chenghu Du;Feng Yu;Minghua Jiang;Ailing Hua;Yaxin Zhao;Xiong Wei;Tao Peng;Xinrong Hu
作者机构：
School of Computer Science and Artificial Intelligence,Wuhan Textile University,Wuhan 430200,China;Engineering Research Center of Hubei Province for Clothing Information,Wuhan 430200,China
文献出处：
引用格式：
[1]Chenghu Du;Feng Yu;Minghua Jiang;Ailing Hua;Yaxin Zhao;Xiong Wei;Tao Peng;Xinrong Hu-.High fidelity virtual try-on network via semantic adaptation and distributed componentization)[J].计算可视媒体（英文）,2022(04):649-663
A类：
componentization,componentized,SMIAN
B类：
High,fidelity,virtual,try,network,via,semantic,adaptation,distributed,Image,systems,have,significant,commercial,value,online,shopping,However,methods,fail,appropriately,handle,details,so,are,defective,maintaining,original,appearance,organizational,items,including,arms,neck,garments,We,novel,high,realistic,results,Specifically,pipeline,used,simultaneous,generation,First,warped,using,thin,plate,splines,TPS,give,coarse,shape,reference,then,corresponding,target,map,generated,which,adaptively,distribution,different,triggered,by,Second,separately,our,image,adjustment,avoid,interference,between,body,parts,Finally,components,integrated,overall,priori,dual,modal,information,incorporated,layers,improve,convergence,Experiments,demonstrate,that,proposed,retain,better,condition,than,current,Our,achieves,convincing,quantitative,qualitative,existing,benchmark,datasets
AB值：
0.575934
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。
