A collection of resources on Image Style Transfer (photorealistic image stylization) and Image-to-image (i2i) translation,
Contributing
Feedback and contributions are welcome! If you think I have missed out on something (or) have any suggestions (papers, implementations and other resources), feel free to pull a request or leave an issue. I will release the latex-pdf version in the future. ⬇️markdown format:
[Paper Name](abs link)
*[Author 1](homepage), Author 2, and Author 3*
**[`Conference/Journal Year`] (`Institution`)** [[Github](link)] [[Project](link)]😄 Now you can use this script to automatically generate the above text.
Unsupervised image-to-image translation (UNIT) aims to translate images from one domain to another without paired data.
Photorealistic image stylization aims at changing style of a photo to that of a reference photo with the constraint that the stylized photo should remain photorealistic.
learn translations between domains, applying to the context of source images a target appearance learned from a dataset.
It has attracted increasing attentions since its widely practical use, such as
-
colorization
-
super resolution
-
semantic synthesis
-
domain adaption
在风格迁移里有一个专门的Loss叫perceptual loss，最早是在 Perceptual losses for real-time style transfer and super-resolution 2016 里被提出
related papers:
citation 4258 Perceptual losses for real-time style transfer and super-resolution
citation 2431 Image Style Transfer Using Convolutional Neural Networks
citation 698 Generating images with perceptual similarity metrics based on deep networks
后来在很多图像里得到应用
-
超分辨率：
Image Super-Resolution by Neural Texture Transfer 2019
Super-resolution with deep convolutional sufficient statistics 2016
Photo-realistic single image super-resolution using a generative adversarial network 2017
EnhanceNet: Single image super-resolution through automated texture synthesis 2017
The order is from the old to the latest
Image-to-Image Translation with Conditional Adversarial Networks
Phillip Isola Jun-Yan Zhu Tinghui Zhou Alexei A. Efros
[CVPR 2017]
Image style transfer using convolutional neural networks
Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
[CVPR 2016] (Tubingen)
Unsupervised Image-to-Image Translation Networks
Ming-Yu Liu, Thomas Breuel, Jan Kautz
[NeurIPS 2017] ()
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros
[ICCV 2017] (UCB)
A Closed-form Solution to Photorealistic Image Stylization
Yijun Li, Ming-Yu Liu, Xueting Li, Ming-Hsuan Yang, Jan Kautz
[ECCV 2018] (UC, NVIDIA) [Github]
CoMoGAN: continuous model-guided image-to-image translation
Fabio Pizzati, Pietro Cerri, Raoul de Charette
[CVPR 2021 (oral)] (Inria) [Github]