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
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 yzzhao2-c@my.cityu.edu.hk.
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:
- 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
- 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)
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}
}