【SR汇总】基于深度学习方法

1、SRCNN、FSRCNN

(Learning a Deep Convolutional Network for Image Super-Resolution, ECCV2014)

(Accelerating the Super-Resolution Convolutional Neural Network, ECCV2016)

2、ESPCN、VESPCN

(Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network, CVPR2016)

(Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation, arxiv 2016)

邻帧的位移偏差+多尺度的Motion estimation

3、VDSR

(Accurate Image Super-Resolution Using Very Deep Convolutional Networks, CVPR2016)

残差网络ResNet，VDSR学习残差结构。

4、DRCN

(Deeply-Recursive Convolutional Network for Image Super-Resolution, CVPR2016)

5、RED

(Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections, NIPS2016)

6、DRRN

(Image Super-Resolution via Deep Recursive Residual Network, CVPR2017)

7、LapSRN

(Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution, CVPR2017)

8、SRDenseNet

(Image Super-Resolution Using Dense Skip Connections, ICCV2017)

9、SRGAN(SRResNet)

(Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, CVPR2017)

对抗学习的代价函数是基于判别器输出的概率。

应当使重建的高分辨率图像与真实的高分辨率图像无论是低层次的像素值上，还是高层次的抽象特征上，和整体概念和风格上，都应当接近。

10、EDSR

(Enhanced Deep Residual Networks for Single Image Super-Resolution, CVPRW2017)

【转载自】

从SRCNN到EDSR，总结深度学习端到端超分辨率方法发展历程（转） - ch07013224的专栏 - CSDN博客 https://blog.csdn.net/ch07013224/article/details/80324312

深度对抗学习在图像分割和超分辨率中的应用 - 知乎 https://zhuanlan.zhihu.com/p/25201511

【其他】

巴特西