Single-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples笔记
来源:互联网 发布:nvh有限元软件 编辑:程序博客网 时间:2024/05/01 07:19
此文2014年TIP。
主要points
double pyramid: a traditional single pyramid and a side pyramid of interpolated levels(figure 5)
对traditional single pyramid,是对input LR image I_L作为I_0多层下采样 I_-n。对 a side pyramid of interpolated levels, 是对上述traditional pyramid 进行插值(scale = p)
则在Fig.5中,左侧pyramid视为高分辨率image,右侧视为下采样再插值得到的same size 的 image.
利用DM(direct mapping)就可以得到映射关系,将低分辨x_i^l恢复为x_i^h。
但是,scale 为 p^n = 1.25^n, 通过层层渐进的方式得到想要的放大倍数。这里面还有一点就是,每次重建之后就把当前重建的样本利用IBP约束,然后还要将结果加入double pyramid作为下次scale渐进的dictionary.
drawback: 文章中说要通过gradual upscalings 来SR,而NP = log_p(s)可能不是想要的放大倍数(不是整数),需要对结果调整大小,但是文章没说具体如何调整。
第一次写,试下效果==
1 0
- Single-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples笔记
- “Single Image Super-resolution using Deformable Patches”
- 《Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network》阅读笔记
- Seven ways to improve example-based single image super resolution笔记
- 图像超分辨EDSR:Enhanced Deep Residual Networks for Single Image Super-Resolution,论文笔记
- 图像超分辨EnhanceNet- Single Image Super-Resolution Through Automated Texture Synthesis笔记
- 《Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network》阅读笔记
- Hyperspectral image super-resolution via non-local sparse tensor factorization
- Enhanced Deep Residual Networks for Single Image Super-Resolution
- Enhanced Deep Residual Networks for Single Image Super-Resolution
- Image Super-Resolution as Sparse Representation of Raw Image Patches
- 基于稀疏表示的图像超分辨率《Image Super-Resolution Via Sparse Representation》
- Deeply-Recursive Convolutional Network for Image Super-Resolution 笔记
- 论文阅读笔记:Image Super-Resolution Using Deep Convolutional Networks
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
- 每日论文Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural
- 一步一步学习IP路由流程
- elasticsearch API 集合
- 【linux开发】Linux下配置java环境 安装eclipse
- Laravel5框架的安装
- 改变R语言默认存储包的路径
- Single-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples笔记
- Android View 的生命周期
- time_t类型和SYSTEMTIME的转换
- sqlserver数据库转为oracle数据库
- libevent学习笔记 ---- 回显服务器 (2)
- SVN版本控制与分支设置
- Xcode6之后添加PCH文件
- C++ typedef的用法
- 在Block中使用weakSelf与strongSelf的意义