Image blending（提升画质）
CVPR 2017 的 GP-GAN: Towards Realistic High-Resolution Image Blending[Paper][Code]
Image Inpainting
1. CVPR 2016的Context-Encoders（CNN+GAN， 鼻祖级的 NN修复方法）
链接： Feature Learning by Inpainting;
Github代码:pathak22/context-encodergithub.com
2. CVPR 2017的High Resolution Inpainting(Context-Encoders+CNNMRF)
链接： High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis;
Github代码: leehomyc/Faster-High-Res-Neural-Inpaintinggithub.com
3.CVPR 2017的 Semantic Image Inpainting with Perceptual and Contextual Losses
4. ICCV 2017的on demanding learning(感觉也是Context-Encoders的衍生版...)
链接：On-Demand Learning for Deep Image Restoration
Github代码:rhgao/on-demand-learninggithub.com
5. SIGGRAPH 2017 (ACM ToG)的Globally and Locally Consistent Image Completion
(CE中加入Global+Local两个判别器的改进)，
Github代码:https://github.com/satoshiiizuka/siggraph2017_inpaintinggithub.com
6. ICLR 2018的New AI Imaging Technique Reconstructs Photos with Realistic Results
Image Inpainting for Irregular Holes UsingPartial Convolutions
号称秒杀PS的AI图像修复神器，来自于Nvidia 研究团队。引入了局部卷积，能够修复任意非中心、不规则区域），代码还没有放出来
论文地址：[1804.07723] Image Inpainting for Irregular Holes Using Partial Convolutionsarxiv.org
7. CVPR 2018的Generative Image Inpainting with Contextual Attention，
一作大佬jiahui Yu 后续还有个工作: Free-Form Image Inpainting with Gated Convolution,
Github代码：JiahuiYu/generative_inpaintinggithub.com
8. ECCV 2018 哈工大左孟旺老师的深度特征重排的图像修复Shift-Net: Image Inpainting via Deep Feature Rearrangement
9.Deep image prior
项目主页：https://dmitryulyanov.github.io/deep_image_prior
适用场景：
1）难以建模图像退化过程
2）难以得到训练图像进行监督训练
10.ECCV 2018的Contextual-based Image Inpainting，inpainting大佬Chao Yang(NPS的一作)等人的又一力作:Contextual-based Image Inpaintingarxiv.org
11.CVPR 2017 的 人脸生成 Generative face completion
13. CVPR2017 的 Semantic Image Inpainting with Perceptual and Contextual Losses
参考链接：
1.https://www.zhihu.com/question/56801298
2.https://blog.csdn.net/muyiyushan/article/details/79093806
3.https://blog.csdn.net/gavinmiaoc/article/details/80802967
4.https://www.52cv.net/?p=315
5.https://github.com/learn2Pro/Learn4xy#image-inpainting
