TensorFlow基础笔记，7 图像风格化效果与性能优化进展

参考

http://hacker.duanshishi.com/?p=1693

http://blog.csdn.net/hungryof/article/details/53981959

http://blog.csdn.net/hungryof/article/details/61195783

http://blog.csdn.net/wyl1987527/article/details/70245214

https://www.ctolib.com/AdaIN-style.html

https://www.leiphone.com/news/201705/ro8EB2entk3vXybM.html(Styles 历史)

http://www.jianshu.com/p/b1189448eb2e

http://blog.csdn.net/wspba/article/details/53994649

Acknowledgement

This project is inspired by many existing style transfer methods and their open-source implementations, including:

• Image Style Transfer Using Convolutional Neural Networks, Gatys et al. [code (by Johnson)]
• A Neural Algorithm of Artistic Style, （原版）
• Texture Synthesis Using Convolutional Neural Networks
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images(改进1)
• Instance Normalization The Missing Ingredient for Fast Stylization
• Deep Identity-aware Transfer of Facial Attributes
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution, Johnson et al. [code]（改进2）
• Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis, Ulyanov et al. [code]
• A Learned Representation For Artistic Style, Dumoulin et al. [code]
• Fast Patch-based Style Transfer of Arbitrary Style, Chen and Schmidt [code] （超越fast style transfer----任意风格图和内容图0.1秒出结果) https://github.com/rtqichen/style-swap
• Controlling Perceptual Factors in Neural Style Transfer, Gatys et al. [code]
• Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization (2017 -- 更快速度) [code]
• deep-photo-styletransfer-master [code]