Code Monkey home page Code Monkey logo

legacy-photo-editing-with-learned-noise-prior's Introduction

Legacy-Photo-Editing-with-Learned-Noise-Prior

The github page for WACV 2021 paper: Legacy Photo Editing with Learned Noise Prior

arxiv version: https://arxiv.org/abs/2011.11309

IEEE/CVF version: https://openaccess.thecvf.com/content/WACV2021/html/Zhao_Legacy_Photo_Editing_With_Learned_Noise_Prior_WACV_2021_paper.html

Legacy Photo Dataset (LP Dataset)

The proposed legacy photo dataset contains approximately 25000 legacy images crawed from the Internet. The images include the real noises. The LP Dataset can only be used for research purpose and any commercial use of the LP Dataset is not allowed.

If you would like to download the LP Dataset data, please fill out an agreement to the LP Dataset Terms of Use and send it to us at [email protected].

Please use the institutional email instead of anonymous addresses such as Gmail, QQMail, and hotmail. Make sure your email address is the same as it in the LP Dataset Terms of Use.

Some training samples are shown like:

Some masked samples are shown like:

Some validation samples are shown like:

Code Usage

Requirement:

  • python 3.6
  • pytorch 1.0.0
  • torchvision 0.2.1
  • cuda 8.0
  • opencv-python 4.2.0.34
  • pytorch_wavelets 1.0.0

Training:

  • negan: you may alter the loss ratio for DWT-based loss for specific dataset; the discriminator of clean image domain can be removed in experiment
  • iegan-inpainting-denoising: perform joint inpainting and denoising
  • iegan-scribble-based-colorization: perform colorization

(currently no pre-trained models provided)

Reference

If you think the paper is helpful for your research, please cite:

@inproceedings{zhao2021legacy,
  title={Legacy Photo Editing with Learned Noise Prior},
  author={Zhao, Yuzhi and Po, Lai-Man and Lin, Tingyu and Wang, Xuehui and Liu, Kangcheng and Zhang, Yujia and Yu, Wing-Yin and Xian, Pengfei and Xiong, Jingjing},
  booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year={2021},
  pages={2103-2112}
}

legacy-photo-editing-with-learned-noise-prior's People

Contributors

zhaoyuzhi avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

legacy-photo-editing-with-learned-noise-prior's Issues

请求大佬指点,万分感谢!

大佬,我借用的您的negan训练了noise的先验分布,下一步我该如何将这个先验分布用在imagenet数据上使其加上mask退化生成训练数据对?在您的文件夹中没有看到明晰的代码?我还看到了model/vgg16.pth 请问这个与训练模型的是pytorch版本直接用吗?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.