数据融合matlab代码-SICE:从多重曝光图像中学习深层单图像对比度增强器（TIP2018）
数据融合matlab代码从多重曝光图像中学习深层单图像对比度增强器
抽象的
由于不良的照明条件和数字成像设备的动态范围有限，因此记录的图像通常曝光不足/曝光过度且对比度较低。
大多数以前的单图像对比度增强（SICE）方法都会调整色调曲线以校正输入图像的对比度。
但是，由于单个图像中的信息有限，这些方法通常无法揭示图像细节。
另一方面，如果我们可以从适当收集的培训数据中学习更多信息，则可以更好地完成SICE任务。
在这项工作中，我们建议使用卷积神经网络（CNN）来训练SICE增强器。
一个关键问题是如何为端到端CNN学习构建低对比度和高对比度图像对的训练数据集。
为此，我们建立了一个大规模的多重曝光图像数据集，其中包含589个精心挑选的高分辨率多重曝光序列和4,413张图像。
采用十三种代表性的多曝光图像融合和基于堆栈的高动态范围成像算法来生成每个序列的对比度增强图像，并进行主观实验以筛选质量最好的图像作为每个场景的参考图像。
利用构建的数据集，可以轻松地将CNN训练为SICE增强器，以改善曝光不足/曝光过度图像的对比度。
实验结果证明了我们的方法相对于现有SICE方法的优势，并且具有很
文件下载
资源详情
[{"title":"（ 80 个子文件 35.09MB ） 数据融合matlab代码-SICE:从多重曝光图像中学习深层单图像对比度增强器（TIP2018）","children":[{"title":"SICE-master","children":[{"title":"README.md <span style='color:#111;'> 3.82KB </span>","children":null,"spread":false},{"title":"Layer","children":[{"title":"ssim_loss_layer.cpp <span style='color:#111;'> 8.69KB </span>","children":null,"spread":false},{"title":"regularization_layer.cu <span style='color:#111;'> 6.15KB </span>","children":null,"spread":false},{"title":"ssim_loss_layer.hpp <span style='color:#111;'> 3.71KB </span>","children":null,"spread":false},{"title":"ssim_loss_layer.cu <span style='color:#111;'> 9.34KB </span>","children":null,"spread":false},{"title":"caffe.proto <span style='color:#111;'> 58.28KB </span>","children":null,"spread":false},{"title":"regularization_layer.cpp <span style='color:#111;'> 5.85KB </span>","children":null,"spread":false},{"title":"regularization_layer.hpp <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false},{"title":"L1_loss_layer.hpp <span style='color:#111;'> 1.25KB </span>","children":null,"spread":false},{"title":"L1_loss_layer.cu <span style='color:#111;'> 1.51KB </span>","children":null,"spread":false},{"title":"L1_loss_layer.cpp <span style='color:#111;'> 1.73KB </span>","children":null,"spread":false}],"spread":true},{"title":"Model 1","children":[{"title":"Readme.md <span style='color:#111;'> 369B </span>","children":null,"spread":false},{"title":"modcrop.m <span style='color:#111;'> 279B </span>","children":null,"spread":false},{"title":"residual.prototxt <span style='color:#111;'> 5.18KB </span>","children":null,"spread":false},{"title":"Test","children":[{"title":"134.JPG <span style='color:#111;'> 2.12MB </span>","children":null,"spread":false},{"title":"352.JPG <span style='color:#111;'> 247.91KB </span>","children":null,"spread":false},{"title":"351.JPG <span style='color:#111;'> 245.57KB </span>","children":null,"spread":false},{"title":"354.JPG <span style='color:#111;'> 865.59KB </span>","children":null,"spread":false},{"title":"0.JPG <span style='color:#111;'> 700.33KB </span>","children":null,"spread":false},{"title":"344.JPG <span style='color:#111;'> 638.73KB </span>","children":null,"spread":false},{"title":"345.JPG <span style='color:#111;'> 841.90KB </span>","children":null,"spread":false},{"title":"3.JPG <span style='color:#111;'> 340.08KB </span>","children":null,"spread":false},{"title":"9.JPG <span style='color:#111;'> 694.47KB </span>","children":null,"spread":false},{"title":"1.JPG <span style='color:#111;'> 258.13KB </span>","children":null,"spread":false},{"title":"68.JPG <span style='color:#111;'> 729.35KB </span>","children":null,"spread":false},{"title":"2.JPG <span style='color:#111;'> 479.83KB </span>","children":null,"spread":false},{"title":"72.JPG <span style='color:#111;'> 375.20KB </span>","children":null,"spread":false},{"title":"79.JPG <span style='color:#111;'> 1.46MB </span>","children":null,"spread":false}],"spread":false},{"title":"Demo_Test.m <span style='color:#111;'> 618B </span>","children":null,"spread":false},{"title":"Model","children":[{"title":"model1.caffemodel <span style='color:#111;'> 2.13MB </span>","children":null,"spread":false}],"spread":true},{"title":"model1.bmp <span style='color:#111;'> 1.32MB </span>","children":null,"spread":false}],"spread":true},{"title":"Model 2","children":[{"title":"Readme.md <span style='color:#111;'> 386B </span>","children":null,"spread":false},{"title":"model2.bmp <span style='color:#111;'> 1.32MB </span>","children":null,"spread":false},{"title":"modcrop.m <span style='color:#111;'> 279B </span>","children":null,"spread":false},{"title":"DataGenerator","children":[{"title":"Readme <span style='color:#111;'> 49B </span>","children":null,"spread":false},{"title":"Demo.m <span style='color:#111;'> 2.14KB </span>","children":null,"spread":false}],"spread":true},{"title":"Test","children":[{"title":"134.JPG <span style='color:#111;'> 2.12MB </span>","children":null,"spread":false},{"title":"352.JPG <span style='color:#111;'> 247.91KB </span>","children":null,"spread":false},{"title":"351.JPG <span style='color:#111;'> 245.57KB </span>","children":null,"spread":false},{"title":"354.JPG <span style='color:#111;'> 865.59KB </span>","children":null,"spread":false},{"title":"0.JPG <span style='color:#111;'> 700.33KB </span>","children":null,"spread":false},{"title":"344.JPG <span style='color:#111;'> 638.73KB </span>","children":null,"spread":false},{"title":"345.JPG <span style='color:#111;'> 841.90KB </span>","children":null,"spread":false},{"title":"3.JPG <span style='color:#111;'> 340.08KB </span>","children":null,"spread":false},{"title":"9.JPG <span style='color:#111;'> 694.47KB </span>","children":null,"spread":false},{"title":"1.JPG <span style='color:#111;'> 258.13KB </span>","children":null,"spread":false},{"title":"68.JPG <span style='color:#111;'> 729.35KB </span>","children":null,"spread":false},{"title":"2.JPG <span style='color:#111;'> 479.83KB </span>","children":null,"spread":false},{"title":"72.JPG <span style='color:#111;'> 375.20KB </span>","children":null,"spread":false},{"title":"79.JPG <span style='color:#111;'> 1.46MB </span>","children":null,"spread":false}],"spread":false},{"title":"Demo_Test.m <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false},{"title":"wlsFilter.m <span style='color:#111;'> 2.46KB </span>","children":null,"spread":false},{"title":"Twostage.prototxt <span style='color:#111;'> 5.33KB </span>","children":null,"spread":false},{"title":"Model","children":[{"title":"model2.caffemodel <span style='color:#111;'> 2.14MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"Model 3","children":[{"title":"Perpixel.prototxt <span style='color:#111;'> 5.66KB </span>","children":null,"spread":false},{"title":"Readme.md <span style='color:#111;'> 476B </span>","children":null,"spread":false},{"title":"modcrop.m <span style='color:#111;'> 279B </span>","children":null,"spread":false},{"title":"Test","children":[{"title":"134.JPG <span style='color:#111;'> 2.12MB </span>","children":null,"spread":false},{"title":"352.JPG <span style='color:#111;'> 247.91KB </span>","children":null,"spread":false},{"title":"351.JPG <span style='color:#111;'> 245.57KB </span>","children":null,"spread":false},{"title":"354.JPG <span style='color:#111;'> 865.59KB </span>","children":null,"spread":false},{"title":"0.JPG <span style='color:#111;'> 700.33KB </span>","children":null,"spread":false},{"title":"344.JPG <span style='color:#111;'> 638.73KB </span>","children":null,"spread":false},{"title":"345.JPG <span style='color:#111;'> 841.90KB </span>","children":null,"spread":false},{"title":"3.JPG <span style='color:#111;'> 340.08KB </span>","children":null,"spread":false},{"title":"9.JPG <span style='color:#111;'> 694.47KB </span>","children":null,"spread":false},{"title":"1.JPG <span style='color:#111;'> 258.13KB </span>","children":null,"spread":false},{"title":"68.JPG <span style='color:#111;'> 729.35KB </span>","children":null,"spread":false},{"title":"2.JPG <span style='color:#111;'> 479.83KB </span>","children":null,"spread":false},{"title":"72.JPG <span style='color:#111;'> 375.20KB </span>","children":null,"spread":false},{"title":"79.JPG <span style='color:#111;'> 1.46MB </span>","children":null,"spread":false}],"spread":false},{"title":"Demo_Test.m <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false},{"title":"wlsFilter.m <span style='color:#111;'> 2.46KB </span>","children":null,"spread":false},{"title":"Layer","children":[{"title":"PixelConv_layer.cu <span style='color:#111;'> 3.26KB </span>","children":null,"spread":false},{"title":"PixelConv_layer.hpp <span style='color:#111;'> 1.79KB </span>","children":null,"spread":false},{"title":"PixelConv_layer.cpp <span style='color:#111;'> 4.89KB </span>","children":null,"spread":false},{"title":"readme.md <span style='color:#111;'> 10B </span>","children":null,"spread":false}],"spread":true},{"title":"model3.bmp <span style='color:#111;'> 1.32MB </span>","children":null,"spread":false},{"title":"Model","children":[{"title":"readme <span style='color:#111;'> 6B </span>","children":null,"spread":false},{"title":"Model3.caffemodel <span style='color:#111;'> 2.50MB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"spread":true}]
评论信息
其他资源
- psd-tool python example
- 分享帖三相桥式全控整流电路的MATLAB仿真-ThreePhase2_0.mdl
- 使用javacc实现基于miniC的语法分析器（完整工程和测试代码）
- download-scannet.py
- web网上花店（含数据库）
- 加窗傅里叶变换的演示 matlab程序 分别对加方窗和海明窗的信号做傅里叶变换
- mysql 的proc 表
- 电机热仿真分析
- C++ 源代码 学生考勤管理系统
- html源代码网页模板文件
- 基于机器学习算法的摔倒检测和日常行为识别研究
- springmvc.docx
- jsr305-3.0.1.jar
- Docker入门-资源总结
- 教育平台源码,开源网校源码,教育系统源码,万岳网校源码ios版
- NoteExpress_Vol_GZZYYDX_3.3.0.8102_zh.exe
- C++ GUI Programming with Qt4
- HCNA-Security-CBSN培训教材
- 四轴飞控源码 PID参考apm 采用了dmp自带解算
- T/CHIA 001-2017手术、操作分类与代码
- 高并发撮合系统
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
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