This is the official MSP code for SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal, which has been accepted by AAAI-2022. This MSP project contains complete training code and test code. In addition, we have provided the Pytorch code, so that you can quickly realize makeup transfer.
At the end of the paper, the additional material section introduces the synthesis process of pseudo-paired data in detail.
├─── dataset # dataset
├── images
├─ non-makeup
├─ makeup
└─ warp # This is where the generated pseudo-paired data is stored
└── seg1
├─ non-makeup
└─ makeup
Modify the 'dataroot' parameter in 'option.py' based on the path location of your own data set.
python train.py
├─── test # test dataset
├── images
├─ non-makeup
└─ makeup
└── seg1
├─ non-makeup
└─ makeup
Modify the 'dataroot' parameter in 'option.py' based on the path location of your own test data set.
python test.py
Please consider citing this project in your publications if it helps your research. The following is a BibTeX reference. The BibTeX entry requires the url LaTeX package.
@InProceedings{Sun_2022_AAAI,
author = {Zhaoyang Sun and Yaxiong Chen and Shengwu Xiong},
title = {SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal},
booktitle = {AAAI},
year = {2022}
}
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。