图像超分辨重建MATLAB源代码(迭代步长自适应)

上传者: 38490884 | 上传时间: 2019-12-21 19:17:58 | 文件大小: 4.61MB | 文件类型: rar
传统的超分辨重建算法往往采用梯度下降法进行求解,迭代时步长往往通过经验确定。而且不同的图像的最优步长往往不相同。步长过大会导致发散,步长过小会导致收敛缓慢。本算法基于对正则化超分辨重建算法实现的基础上,对步长的选取进行了优化,推导出了每次迭代时的最优步长大小,并将其自适应化,改进了超分辨算法的收敛性,从而能够在更短的时间内取得更加精确的重建结果。相关具体内容请参考对应的论文: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.

文件下载

资源详情

[{"title":"( 32 个子文件 4.61MB ) 图像超分辨重建MATLAB源代码(迭代步长自适应)","children":[{"title":"Wang2018Fast","children":[{"title":"cal_ssim.m <span style='color:#111;'> 6.62KB </span>","children":null,"spread":false},{"title":"Set","children":[{"title":"04.bmp <span style='color:#111;'> 768.05KB </span>","children":null,"spread":false},{"title":"14.bmp <span style='color:#111;'> 1014.80KB </span>","children":null,"spread":false},{"title":"02.bmp <span style='color:#111;'> 768.05KB </span>","children":null,"spread":false},{"title":"13.bmp <span style='color:#111;'> 1.13MB </span>","children":null,"spread":false},{"title":"07.bmp <span style='color:#111;'> 527.40KB </span>","children":null,"spread":false},{"title":"09.bmp <span style='color:#111;'> 243.05KB </span>","children":null,"spread":false},{"title":"08.bmp <span style='color:#111;'> 261.62KB </span>","children":null,"spread":false},{"title":"01.bmp <span style='color:#111;'> 1.19MB </span>","children":null,"spread":false},{"title":"16.bmp <span style='color:#111;'> 257.05KB </span>","children":null,"spread":false},{"title":"11.bmp <span style='color:#111;'> 229.74KB </span>","children":null,"spread":false},{"title":"06.bmp <span style='color:#111;'> 663.90KB </span>","children":null,"spread":false},{"title":"18.bmp <span style='color:#111;'> 768.05KB </span>","children":null,"spread":false},{"title":"03.bmp <span style='color:#111;'> 768.05KB </span>","children":null,"spread":false},{"title":"17.bmp <span style='color:#111;'> 297.05KB </span>","children":null,"spread":false},{"title":"05.bmp <span style='color:#111;'> 703.18KB </span>","children":null,"spread":false},{"title":"10.bmp <span style='color:#111;'> 229.83KB </span>","children":null,"spread":false},{"title":"12.bmp <span style='color:#111;'> 192.12KB </span>","children":null,"spread":false},{"title":"15.bmp <span style='color:#111;'> 297.05KB </span>","children":null,"spread":false}],"spread":false},{"title":"line_search.m <span style='color:#111;'> 724B </span>","children":null,"spread":false},{"title":"ImWarp.m <span style='color:#111;'> 437B </span>","children":null,"spread":false},{"title":"Wang_SR.m <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"Demo_run.m <span style='color:#111;'> 3.47KB </span>","children":null,"spread":false},{"title":"ImDegrate.m <span style='color:#111;'> 478B </span>","children":null,"spread":false},{"title":"Tikhonov.m <span style='color:#111;'> 165B </span>","children":null,"spread":false},{"title":"Gradient_BTV.m <span style='color:#111;'> 349B </span>","children":null,"spread":false},{"title":"~$正则表.docx <span style='color:#111;'> 162B </span>","children":null,"spread":false},{"title":"LR2HR.m <span style='color:#111;'> 341B </span>","children":null,"spread":false},{"title":"HR2LR.m <span style='color:#111;'> 288B </span>","children":null,"spread":false},{"title":"shift.m <span style='color:#111;'> 2.43KB </span>","children":null,"spread":false},{"title":"L2GradientBackProject.m <span style='color:#111;'> 536B </span>","children":null,"spread":false},{"title":"readme.txt <span style='color:#111;'> 2.21KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

  • 逝水之痕 :
    谢谢分享,能发SCI的方法多少都会有明显优点,所以可以提前好评
    2020-05-17
  • weixin_43908377 :
    这个资料非常好用
    2019-12-12
  • combstudio :
    请问这个需要训练样本集吗?
    2019-08-20
  • qq_40074189 :
    很不错的代码呀
    2019-05-15
  • qq_37001617 :
    还没用过,用过再评价
    2019-04-18

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明