典型文献
Self-supervised image blind deblurring using deep generator prior
文献摘要：
Deep generative prior(DGP)is recently proposed for image restoration and manipulation,obtaining compelling results for recovering missing semantics.In this paper,we exploit a general solution for single image deblurring using DGP as the image prior.To this end,two aspects of this object are investigated.One is modeling the process of latent image degradation,corresponding to the estimation of blur kernels in conventional deblurring methods.In this regard,a Re-blur2Deblur network is proposed and trained on large-scale datasets.In this way,the proposed structure can simulate the degradation of latent sharp images.The other is encouraging deblurring results faithful to the content of latent im-ages,and matching the appearance of blurry observations.As the generative adversarial network(GAN)-based me-thods often result in mismatched reconstruction,a deblurring framework with the relaxation strategy is implemented to tackle this problem.The pre-trained GAN and pre-trained ReblurNet are allowed to be fine-tuned on the fly in a self-supervised manner.Finally,we demonstrate empirically that the proposed model can perform favorably against the state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
LI Yuan;WANG Shasha;CHEN Lei
作者机构：
School of Software,Henan University,Kaifeng 475004,China;School of Electronic and Electrical Engineering,Shangqiu Normal University,Shangqiu 476000,China
文献出处：
引用格式：
[1]LI Yuan;WANG Shasha;CHEN Lei-.Self-supervised image blind deblurring using deep generator prior)[J].光电子快报（英文版）,2022(03):187-192
A类：
blur2Deblur,ReblurNet
B类：
Self,supervised,blind,deblurring,using,deep,generator,prior,Deep,generative,DGP,recently,proposed,restoration,manipulation,obtaining,compelling,results,recovering,missing,semantics,In,this,paper,exploit,general,solution,single,To,end,aspects,object,are,investigated,One,modeling,process,latent,degradation,corresponding,estimation,kernels,conventional,methods,regard,network,trained,large,scale,datasets,way,structure,can,simulate,sharp,images,other,encouraging,faithful,content,matching,appearance,blurry,observations,adversarial,GAN,often,mismatched,reconstruction,framework,relaxation,strategy,implemented,tackle,problem,pre,allowed,be,fine,tuned,fly,self,manner,Finally,demonstrate,empirically,that,perform,favorably,against,state,art
AB值：
0.552689
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。
