CVPR2018_Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning

http://mmlab.ie.cuhk.edu.hk/projects/RL-Restore/

强化学习的入门介绍：https://blog.csdn.net/aliceyangxi1987/article/details/73327378

https://www.zhihu.com/question/41775291

CNN在low-level的问题处理前沿：

deblurring：	S. Nah, T. H. Kim, and K. M. Lee. Deep multi-scale convolutional neural network for dynamic scene deblurring. In CVPR, 2017.
J. Sun, W. Cao, Z. Xu, and J. Ponce. Learning a convolutional neural network for non-uniform motion blur removal. In CVPR, 2015.
L. Xu, X. Tao, and J. Jia. Inverse kernels for fast spatial deconvolution. In ECCV, 2014.
denoising：	Y. Chen,W. Yu, and T. Pock. On learning optimized reaction diffusion processes for effective image restoration. In CVPR, 2015.
S. Lefkimmiatis. Non-local color image denoising with convolutional neural networks. In CVPR, 2017.
Z. Wang, D. Liu, S. Chang, Q. Ling, Y. Yang, and T. S. Huang. D3: Deep dual-domain based fast restoration of JPEG-compressed images. In CVPR, 2016.
JPEG artifacts reduction：	C. Dong, Y. Deng, C. C. Loy, and X. Tang. Compression artifacts reduction by a deep convolutional network. In ICCV, 2015.
J. Guo and H. Chao. Building dual-domain representations for compression artifacts reduction. In ECCV, 2016.
Z. Wang, D. Liu, S. Chang, Q. Ling, Y. Yang, and T. S. Huang. D3: Deep dual-domain based fast restoration of JPEG-compressed images. In CVPR, 2016.
super-resolution：	C. Dong, C. C. Loy, K. He, and X. Tang. Image superresolution using deep convolutional networks. TPAMI, 38(2):295–307, 2016.
T.-W. Hui, C. C. Loy, and X. Tang. Depth map superresolution by deep multi-scale guidance. In ECCV, 2016.
J. Kim, J. Kwon Lee, and K. Mu Lee. Accurate image superresolution using very deep convolutional networks. In CVPR, 2016.
J. Kim, J. Kwon Lee, and K. Mu Lee. Deeply-recursive convolutional network for image super-resolution. In CVPR, 2016.
W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang. Deep laplacian pyramid networks for fast and accurate superresolution. In CVPR, 2017.
Y. Tai, J. Yang, and X. Liu. Image super-resolution via deep recursive residual network. In CVPR, 2017.
Y. Tai, J. Yang, X. Liu, and C. Xu. Memnet: A persistent memory network for image restoration. In ICCV, 2017.
X. Wang, K. Yu, C. Dong, and C. C. Loy. Recovering realistic texture in image super-resolution by deep spatial feature transform. In CVPR, 2018.

PSNR:

CVPR2018_Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning-LMLPHP

详细解释，读下面的链接：

http://www.360doc.com/content/16/0919/12/496343_591970301.shtml

独热码，在英文文献中称做 one-hot code, 直观来说就是有多少个状态就有多少比特，而且只有一个比特为1，其他全为0的一种码制，更加详细参加one_hot code（维基百科）。在机器学习中对于离散型的分类型的数据，需要对其进行数字化比如说性别这一属性，只能有男性或者女性或者其他这三种值，如何对这三个值进行数字化表达？一种简单的方式就是男性为0，女性为1，其他为2，这样做有什么问题？

长短期记忆（Long-Short Term Memory, LSTM）是一种时间递归神经网络(RNN)，论文首次发表于1997年。由于独特的设计结构，LSTM适合于处理和预测时间序列中间隔和延迟非常长的重要事件。

http://www.cnblogs.com/wangduo/p/6773601.html