mirror of https://github.com/menyifang/DCT-Net
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
33 lines
1.2 KiB
Markdown
33 lines
1.2 KiB
Markdown
# DCT-Net: Domain-Calibrated Translation for Portrait Stylization
|
|
|
|
### [Project page](https://menyifang.github.io/projects/DCTNet/DCTNet.html) | [Video](https://www.youtube.com/watch?v=Y8BrfOjXYQM) | [Paper](https://arxiv.org/abs/2207.02426)
|
|
|
|
Official implementation of DCT-Net for Portrait Stylization.
|
|
|
|
|
|
> [**DCT-Net: Domain-Calibrated Translation for Portrait Stylization**](arxiv_url_coming_soon),
|
|
> Yifang Men(https://menyifang.github.io/)<sup>1</sup>, Yuan Yao<sup>1</sup>, Miaomiao Cui<sup>1</sup>, Zhouhui Lian(https://www.icst.pku.edu.cn/zlian/)<sup>2</sup>, Xuansong Xie<sup>1</sup>
|
|
> _<sup>1</sup>[DAMO Academy, Alibaba Group](https://damo.alibaba.com), Beijing, China_
|
|
> _<sup>2</sup>[Wangxuan Institute of Computer Technology, Peking University](http://www.comp.polyu.edu.hk](https://www.icst.pku.edu.cn/), China_
|
|
> In: SIGGRAPH 2022 (**TOG**)
|
|
> *arXiv preprint (https://arxiv.org/abs/2207.02426)*
|
|
|
|
|
|
## Demo
|
|
Full-body translation in multi-styles & Video stylization
|
|
<table>
|
|
<tr>
|
|
<td><img src="assets/demo_style.gif" width="100%"/></td>
|
|
<td><img src="assets/demo_video.gif" width="100%"/></td>
|
|
</tr>
|
|
</table>
|
|
|
|
## News
|
|
(2022-07-07) The paper is available now at arxiv(https://arxiv.org/abs/2207.02426).
|
|
|
|
|
|
## Requirements
|
|
|
|
|
|
## Quick Start
|