原文:https://github.com/ycjing/Neural-Style-Transfer-Papers

Neural-Style-Transfer-Papers

Selected papers, corresponding codes and pre-trained models in our review paper "Neural Style Transfer: A Review"

Citation

If you find this repository useful for your research, please cite

@article{jing2017neural,
title={Neural Style Transfer: A Review},
author={Jing, Yongcheng and Yang, Yezhou and Feng, Zunlei and Ye, Jingwen and Song, Mingli},
journal={arXiv preprint arXiv:1705.04058},
year={2017}
}

Pre-trained Models in Our Paper

✅[Coming Soon]

A Taxonomy of Current Methods

1. Descriptive Neural Methods Based On Image Iteration

1.1. MMD-based Descriptive Neural Methods

✅ [A Neural Algorithm of Artistic Style] [Paper] (First Neural Style Transfer Paper)

❇️ Code:

✅ [Image Style Transfer Using Convolutional Neural Networks] [Paper] (CVPR 2016)

✅ [Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses] [Paper] (CVPR 2017)

✅ [Demystifying Neural Style Transfer] [Paper] (Theoretical Explanation) (IJCAI 2017)

❇️ Code:

✅ [Content-Aware Neural Style Transfer] [Paper]

✅ [Towards Deep Style Transfer: A Content-Aware Perspective] [Paper] (BMVC 2016)

1.2. MRF-based Descriptive Neural Methods

✅ [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis] [Paper] (CVPR 2016)

❇️ Code:

✅ [Neural Doodle_Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork] [Paper]

2. Generative Neural Methods Based On Model Iteration

✅ [Perceptual Losses for Real-Time Style Transfer and Super-Resolution] [Paper] (ECCV 2016)

❇️ Code:

❇️ Pre-trained Models:

✅ [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images] [Paper] (ICML 2016)

❇️ Code:

✅ [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis] [Paper] (CVPR 2017)

❇️ Code:

✅ [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks] [Paper] (ECCV 2016)

❇️ Code:

✅ [A Learned Representation for Artistic Style] [Paper] (ICLR 2017)

❇️ Code:

✅ [Fast Patch-based Style Transfer of Arbitrary Style] [Paper]

❇️ Code:

Slight Modifications of Current Methods

1. Modifications of Descriptive Neural Methods

✅ [Exploring the Neural Algorithm of Artistic Style] [Paper]

✅ [Improving the Neural Algorithm of Artistic Style] [Paper]

✅ [Preserving Color in Neural Artistic Style Transfer] [Paper]

✅ [Controlling Perceptual Factors in Neural Style Transfer] [Paper]

❇️ Code:

2. Modifications of Generative Neural Methods

✅ [Instance Normalization:The Missing Ingredient for Fast Stylization] [Paper]

❇️ Code:

✅ [Depth-Preserving Style Transfer] [Paper]

❇️ Code:

Extensions to Specific Types of Images

✅ [Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artwork] [Paper]

❇️ Code:

✅ [Painting Style Transfer for Head Portraits Using Convolutional Neural Networks] [Paper] (SIGGRAPH 2016)

✅ [Son of Zorn's Lemma Targeted Style Transfer Using Instance-aware Semantic Segmentation] [Paper]

✅ [Artistic Style Transfer for Videos] [Paper] (GCPR 2016)

❇️ Code:

✅ [DeepMovie: Using Optical Flow and Deep Neural Networks to Stylize Movies] [Paper]

Application

✅ Prisma

✅ Ostagram

❇️ Code:

✅ Deep Forger

Application Papers

✅ [Bringing Impressionism to Life with Neural Style Transfer in Come Swim] [Paper]

✅ [Imaging Novecento. A Mobile App for Automatic Recognition of Artworks and Transfer of Artistic Styles] [Paper]

Blogs

✅ https://code.facebook.com/posts/196146247499076/delivering-real-time-ai-in-the-palm-of-your-hand/

✅ https://research.googleblog.com/2016/10/supercharging-style-transfer.html

Exciting New Directions

✅ Character Style Transfer

  • [Awesome Typography: Statistics-based Text Effects Transfer][Paper]

  • [Rewrite: Neural Style Transfer For Chinese Fonts][Project]

神经风格转换 (Neural-Style-Transfer-Papers)的更多相关文章

  1. 神经风格转换Neural Style Transfer a review

    原文:http://mp.weixin.qq.com/s/t_jknoYuyAM9fu6CI8OdNw 作者:Yongcheng Jing 等 机器之心编译 风格迁移是近来人工智能领域内的一个热门研究 ...

  2. 项目总结四:神经风格迁移项目(Art generation with Neural Style Transfer)

    1.项目介绍 神经风格转换 (NST) 是深部学习中最有趣的技术之一.它合并两个图像, 即 内容图像 C(content image) 和 样式图像S(style image), 以生成图像 G(ge ...

  3. fast neural style transfer图像风格迁移基于tensorflow实现

    引自:深度学习实践:使用Tensorflow实现快速风格迁移 一.风格迁移简介 风格迁移(Style Transfer)是深度学习众多应用中非常有趣的一种,如图,我们可以使用这种方法把一张图片的风格“ ...

  4. 课程四(Convolutional Neural Networks),第四 周(Special applications: Face recognition & Neural style transfer) —— 2.Programming assignments:Art generation with Neural Style Transfer

    Deep Learning & Art: Neural Style Transfer Welcome to the second assignment of this week. In thi ...

  5. [C4W4] Convolutional Neural Networks - Special applications: Face recognition & Neural style transfer

    第四周:Special applications: Face recognition & Neural style transfer 什么是人脸识别?(What is face recogni ...

  6. DeepLearning.ai-Week4-Deep Learning & Art: Neural Style Transfer

    1 - Task Implement the neural style transfer algorithm Generate novel artistic images using your alg ...

  7. DeepLearning.ai学习笔记(四)卷积神经网络 -- week4 特殊应用:人力脸识别和神经风格转换

    一.什么是人脸识别 老实说这一节中的人脸识别技术的演示的确很牛bi,但是演技好尴尬,233333 啥是人脸识别就不用介绍了,下面笔记会介绍如何实现人脸识别. 二.One-shot(一次)学习 假设我们 ...

  8. Art: Neural Style Transfer

    Andrew Ng deeplearning courese-4:Convolutional Neural Network Convolutional Neural Networks: Step by ...

  9. 课程四(Convolutional Neural Networks),第四 周(Special applications: Face recognition & Neural style transfer) —— 1.Practice quentions

    [解释] This allows us to learn to predict a person’s identity using a softmax output unit, where the n ...

随机推荐

  1. 通过jvm 查看死锁

    jstack -l jvm_pid 运行以下代码之后运行上面命令,可以在控制台上看到死锁. public class DeadLock { public static String obj1 = &q ...

  2. ES排序值相同顺序随机的问题

    ES排序值相同顺序随机的问题 code[class*="language-"] { padding: .1em; border-radius: .3em; white-space: ...

  3. 算法中Amortised time的理解

    ref:http://stackoverflow.com/questions/200384/constant-amortized-time 如果非要翻译成中文,我觉得摊算时间或均摊时间(注意,它和平均 ...

  4. lua源码学习篇三:赋值表达式解析的流程

    上节说到表达式的解析问题,exprstate函数用于解析普通的赋值表达式.lua语言支持多变量赋值.本文先从单变量赋值表达式讲起. a = b = c = a + b 对于简单的两个数的求和过程,lu ...

  5. Openstack_单元测试

    目录 目录 单元测试的原理 单元测试的实现 最后 单元测试的原理 单元测试中的单元可以是一个模块文件, 测试的内容就是模块自身的代码(非导入型代码)是否正确执行. 其中包含了测试代码的正反向逻辑是否正 ...

  6. 【疑难杂症】Firefox 火狐浏览器 抓不到本地数据包

    日期:2019-05-17 23:28:11 介绍:火狐浏览器,如何才能够抓到本地(127.0.0.1)的数据包? 0x01.问题描述 在 Firefox 上安装了证书,浏览器也可以正常抓取互联网的 ...

  7. 旅游局nginx配置

    #user nobody;worker_processes 1; #error_log logs/error.log;#error_log logs/error.log notice;#error_l ...

  8. 打印一个浮点数组,会输出字符串"Hello, world“ & 浮点数的二进制表示(IEEE 754标准)

    #include <stdio.h> #include<stdlib.h> int main() { float a[3] = { 1143139122437582505939 ...

  9. 【MM系列】SAP MM模块-货物移动对标准价的影响

    公众号:SAP Technical 本文作者:matinal 原文出处:http://www.cnblogs.com/SAPmatinal/ 原文链接:[MM系列]SAP MM模块-货物移动对标准价的 ...

  10. 第五周实验报告&学习总结

    实验三 String类的应用 实验目的 掌握类String类的使用: 学会使用JDK帮助文档: 实验内容 1.已知字符串:"this is a test of java".按要求执 ...