91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

資源簡介

傳統的超分辨重建算法往往采用梯度下降法進行求解,迭代時步長往往通過經驗確定。而且不同的圖像的最優步長往往不相同。步長過大會導致發散,步長過小會導致收斂緩慢。本算法基于對正則化超分辨重建算法實現的基礎上,對步長的選取進行了優化,推導出了每次迭代時的最優步長大小,并將其自適應化,改進了超分辨算法的收斂性,從而能夠在更短的時間內取得更加精確的重建結果。相關具體內容請參考對應的論文:Yingqian Wang, Jungang Yang, Chao Xiao, and Wei An, "Fast convergence strategy for multi-image superresolution via adaptive line search," IEEE Access, vol. 6, no. 1, pp. 9129-9139.

資源截圖

代碼片段和文件信息

function?ssim?=?cal_ssim(?im1?im2?b_row?b_col)

[h?w?ch]?=?size(?im1?);
ssim?=?0;
if?(ch?==?1)
????ssim?=?ssim_index?(?im1(b_row+1:h-b_row?b_col+1:w-b_col)?im2(b_row+1:h-b_rowb_col+1:w-b_col));
else
????for?i?=?1:ch
????????ssim?=?ssim?+?ssim_index?(?im1(b_row+1:h-b_row?b_col+1:w-b_col?i)?im2(b_row+1:h-b_rowb_col+1:w-b_col?i));
????end
????ssim?=?ssim/3;
end
return

function?[mssim?ssim_map]?=?ssim_index(img1?img2?K?window?L)

%?========================================================================
%?SSIM?Index?with?automatic?downsampling?Version?1.0
%?Copyright(c)?2009?Zhou?Wang
%?All?Rights?Reserved.
%
%?----------------------------------------------------------------------
%?Permission?to?use?copy?or?modify?this?software?and?its?documentation
%?for?educational?and?research?purposes?only?and?without?fee?is?hereby
%?granted?provided?that?this?copyright?notice?and?the?original?authors‘
%?names?appear?on?all?copies?and?supporting?documentation.?This?program
%?shall?not?be?used?rewritten?or?adapted?as?the?basis?of?a?commercial
%?software?or?hardware?product?without?first?obtaining?permission?of?the
%?authors.?The?authors?make?no?representations?about?the?suitability?of
%?this?software?for?any?purpose.?It?is?provided?“as?is“?without?express
%?or?implied?warranty.
%----------------------------------------------------------------------
%
%?This?is?an?implementation?of?the?algorithm?for?calculating?the
%?Structural?SIMilarity?(SSIM)?index?between?two?images
%
%?Please?refer?to?the?following?paper?and?the?website?with?suggested?usage
%
%?Z.?Wang?A.?C.?Bovik?H.?R.?Sheikh?and?E.?P.?Simoncelli?“Image
%?quality?assessment:?From?error?visibility?to?structural?similarity“
%?IEEE?Transactios?on?Image?Processing?vol.?13?no.?4?pp.?600-612
%?Apr.?2004.
%
%?http://www.ece.uwaterloo.ca/~z70wang/research/ssim/
%
%?Note:?This?program?is?different?from?ssim_index.m?where?no?automatic
%?downsampling?is?performed.?(downsampling?was?done?in?the?above?paper
%?and?was?described?as?suggested?usage?in?the?above?website.)
%
%?Kindly?report?any?suggestions?or?corrections?to?zhouwang@ieee.org
%
%----------------------------------------------------------------------
%
%Input?:?(1)?img1:?the?first?image?being?compared
%????????(2)?img2:?the?second?image?being?compared
%????????(3)?K:?constants?in?the?SSIM?index?formula?(see?the?above
%????????????reference).?defualt?value:?K?=?[0.01?0.03]
%????????(4)?window:?local?window?for?statistics?(see?the?above
%????????????reference).?default?widnow?is?Gaussian?given?by
%????????????window?=?fspecial(‘gaussian‘?11?1.5);
%????????(5)?L:?dynamic?range?of?the?images.?default:?L?=?255
%
%Output:?(1)?mssim:?the?mean?SSIM?index?value?between?2?images.
%????????????If?one?of?the?images?being?compared?is?regarded?as?
%????????????perfect?quality?then?mssim?can?be?considered?as?the
%????????????quality?measure?of?the?other?image.
%????????????I

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件???????6779??2017-10-07?11:07??Wang2018Fast\cal_ssim.m

?????文件???????3554??2018-05-23?21:20??Wang2018Fast\Demo_run.m

?????文件????????349??2018-05-23?21:18??Wang2018Fast\Gradient_BTV.m

?????文件????????288??2018-05-23?21:19??Wang2018Fast\HR2LR.m

?????文件????????478??2018-05-23?21:16??Wang2018Fast\ImDegrate.m

?????文件????????437??2018-05-23?21:17??Wang2018Fast\ImWarp.m

?????文件????????536??2018-05-23?21:18??Wang2018Fast\L2GradientBackProject.m

?????文件????????724??2018-05-23?21:18??Wang2018Fast\line_search.m

?????文件????????341??2018-05-23?21:19??Wang2018Fast\LR2HR.m

?????文件???????2263??2018-05-23?21:13??Wang2018Fast\readme.txt

?????文件????1244214??2013-10-06?16:07??Wang2018Fast\Set\01.bmp

?????文件?????786486??2013-10-06?16:07??Wang2018Fast\Set\02.bmp

?????文件?????786486??2013-10-06?16:07??Wang2018Fast\Set\03.bmp

?????文件?????786486??2013-10-06?16:07??Wang2018Fast\Set\04.bmp

?????文件?????720054??2013-10-06?16:07??Wang2018Fast\Set\05.bmp

?????文件?????679830??2017-10-21?07:57??Wang2018Fast\Set\06.bmp

?????文件?????540054??2017-10-21?07:58??Wang2018Fast\Set\07.bmp

?????文件?????267894??2017-10-21?19:02??Wang2018Fast\Set\08.bmp

?????文件?????248886??2013-10-06?16:07??Wang2018Fast\Set\09.bmp

?????文件?????235350??2013-10-06?16:07??Wang2018Fast\Set\10.bmp

?????文件?????235254??2013-10-06?16:07??Wang2018Fast\Set\11.bmp

?????文件?????196730??2013-10-06?16:07??Wang2018Fast\Set\12.bmp

?????文件????1179702??2013-10-06?16:07??Wang2018Fast\Set\13.bmp

?????文件????1039158??2017-11-02?16:55??Wang2018Fast\Set\14.bmp

?????文件?????304182??2013-10-06?16:07??Wang2018Fast\Set\15.bmp

?????文件?????263222??2013-10-06?16:07??Wang2018Fast\Set\16.bmp

?????文件?????304182??2013-10-06?16:07??Wang2018Fast\Set\17.bmp

?????文件?????786486??2013-10-06?16:07??Wang2018Fast\Set\18.bmp

?????文件???????2493??2017-04-15?11:13??Wang2018Fast\shift.m

?????文件????????165??2018-05-23?21:18??Wang2018Fast\Tikhonov.m

............此處省略7個文件信息

評論

共有 條評論