典型文献
TSR:algorithm of image hole-filling based on three-step repairing
文献摘要：
In order to solve the hole-filling mismatch problem in virtual view synthesis,a three-step repairing(TSR)algorithm was proposed.Firstly,the image with marked holes is decomposed by the non-subsampled shear wave transform(NSST),which will generate high-/low-frequency sub-images with different resolutions.Then the improved Criminisi algorithm was used to repair the texture information in the high-frequency sub-images,while the improved curvature driven diffusion(CDD)algorithm was used to repair the low-frequency sub-images with the image structure information.Finally,the repaired parts of high-frequency and low-frequency sub-images are synthesized to obtain the final image through inverse NSST.Experiments show that the peak signal-to-noise ratio(PSNR)of the TSR algorithm is improved by an average of 2-3 dB and 1-2 dB compared with the Criminisi algorithm and the nearest neighbor interpolation(NNI)algorithm,respectively.
文献关键词：
中图分类号：
作者姓名：
Li Fucheng;Deng Junyong;Zhu Yun;Luo Jiaying;Ren Han
作者机构：
School of Electronic Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China
文献出处：
引用格式：
[1]Li Fucheng;Deng Junyong;Zhu Yun;Luo Jiaying;Ren Han-.TSR:algorithm of image hole-filling based on three-step repairing)[J].中国邮电高校学报（英文版）,2022(05):83-91
A类：
B类：
TSR,algorithm,filling,three,step,repairing,In,order,solve,mismatch,problem,virtual,view,synthesis,was,proposed,Firstly,marked,holes,decomposed,by,subsampled,shear,wave,transform,NSST,which,will,generate,high,low,frequency,images,different,resolutions,Then,improved,Criminisi,used,texture,information,while,curvature,driven,diffusion,CDD,structure,Finally,repaired,parts,synthesized,obtain,final,through,inverse,Experiments,show,that,peak,signal,noise,ratio,PSNR,average,dB,compared,nearest,neighbor,interpolation,NNI,respectively
AB值：
0.536742
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。
