説明なし

Liu Ziang e07e99c9e7 Update SimSwap colab.ipynb 4 年 前
crop_224 3ee304b0e1 update 4 年 前
data 01a8d6d0a6 init 4 年 前
demo_file 29f9bb6d0e Demo image or video 4 年 前
doc 77175e4f5a update 4 年 前
insightface_func 6e5ee6a3f6 Insightface: used to detect and align faces 4 年 前
models 01a8d6d0a6 init 4 年 前
options b394ffdffd Updated 4 年 前
output 3ee304b0e1 update 4 年 前
simswaplogo b394ffdffd Updated 4 年 前
util dbcfc9a44b Some related scripts for face swapping. 4 年 前
.gitattributes a0dab0c7b1 Initial commit 4 年 前
.gitignore a887c06799 update 4 年 前
LICENSE 2d4c69790f Update LICENSE 4 年 前
README.md 439f6ff94f Update README.md 4 年 前
SimSwap colab.ipynb e07e99c9e7 Update SimSwap colab.ipynb 4 年 前
test_one_image.py 33338116c8 Update test_one_image.py 4 年 前
test_video_swapmutil.py f593abe74f Script for video face swapping 4 年 前
test_video_swapsingle.py 24dc3df134 Script for video face swapping 4 年 前
test_wholeimage_swapmutil.py c964d806e7 Script for image face swapping 4 年 前
test_wholeimage_swapsingle.py 9d186aec16 Script for image face swapping 4 年 前

README.md

SimSwap: An Efficient Framework For High Fidelity Face Swapping

Proceedings of the 28th ACM International Conference on Multimedia

The official repository with Pytorch

*Our method can realize arbitrary face swapping on images and videos with one single trained model.*

Currently, only the test code is available. Training scripts are coming soon

simswaplogo

Our paper can be downloaded from [Arxiv] [ACM DOI]

Top News

2021-06-20: We release the scripts for arbitrary video and image processing, and a colab demo.

Dependencies

  • python3.6+
  • pytorch1.5+
  • torchvision
  • opencv
  • pillow
  • numpy
  • imageio
  • moviepy
  • insightface

Usage

Preparation

Inference for image or video face swapping

Colab demo

Training: coming soon

Video

Results

Results1

Results2

High-quality videos can be found in the link below:

[Mama(video) 1080p]

[Google Drive link for video 1]

[Google Drive link for video 2]

[Google Drive link for video 3]

[Baidu Drive link for video] Password: b26n

[Online Video]

User case

If you have some interesting results after using our project and are willing to share, you can contact us by email or share directly on the issue. Later, we may make a separate section to show these results, which should be cool.

At the same time, if you have suggestions for our project, please feel free to ask questions in the issue, or contact us directly via email: email1, email2, email3. (All three can be contacted, just choose any one)

To cite our paper

@inproceedings{DBLP:conf/mm/ChenCNG20,
  author    = {Renwang Chen and
               Xuanhong Chen and
               Bingbing Ni and
               Yanhao Ge},
  title     = {SimSwap: An Efficient Framework For High Fidelity Face Swapping},
  booktitle = {{MM} '20: The 28th {ACM} International Conference on Multimedia},
  pages     = {2003--2011},
  publisher = {{ACM}},
  year      = {2020},
  url       = {https://doi.org/10.1145/3394171.3413630},
  doi       = {10.1145/3394171.3413630},
  timestamp = {Thu, 15 Oct 2020 16:32:08 +0200},
  biburl    = {https://dblp.org/rec/conf/mm/ChenCNG20.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Related Projects

Please visit our another ACMMM2020 high-quality style transfer project

logo

title

Learn about our other projects [RainNet];

[Sketch Generation];

[CooGAN];

[Knowledge Style Transfer];

[SimSwap];

[ASMA-GAN];

[SNGAN-Projection-pytorch]

[Pretrained_VGG19].

Acknowledgements