Sen descrición

chenxuanhong 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
crop_224 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
data 01a8d6d0a6 init %!s(int64=4) %!d(string=hai) anos
doc ad5029eba5 update %!s(int64=4) %!d(string=hai) anos
models 01a8d6d0a6 init %!s(int64=4) %!d(string=hai) anos
options 01a8d6d0a6 init %!s(int64=4) %!d(string=hai) anos
output 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
util 01a8d6d0a6 init %!s(int64=4) %!d(string=hai) anos
.gitattributes a0dab0c7b1 Initial commit %!s(int64=4) %!d(string=hai) anos
.gitignore 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
AdaptiveAvgPool2d.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
BatchNorm1d.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
BatchNorm2d.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
Conv2d.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
DataParallel.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
Dropout.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
LICENSE a0dab0c7b1 Initial commit %!s(int64=4) %!d(string=hai) anos
Linear.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
MaxPool2d.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
PReLU.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
README.md 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
Sequential.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
Sigmoid.patch 3ee304b0e1 update %!s(int64=4) %!d(string=hai) anos
test_one_image.py 01a8d6d0a6 init %!s(int64=4) %!d(string=hai) anos

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

Currently, only the test code is available, and training scripts are coming soon

[Conference paper]

Results

Results1

Results2

Video

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

[Baidu Drive link for video] Password: b26n

Dependencies

  • python3.6+
  • pytorch1.5+
  • torchvision
  • opencv
  • pillow
  • numpy

Usage

To test the pretrained model

python test_one_image.py --isTrain false  --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/

--name refers to the SimSwap training logs name.

Pretrained model

Usage

There are two archive files in the drive: checkpoints.zip and arcface_checkpoint.tar

  • Copy the arcface_checkpoint.tar into ./arcface_model
  • Unzip checkpoints.zip, place it in the root dir ./

[Google Drive]

[Baidu Drive] Password: jd2v

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

Learn about our other projects [RainNet], [Sketch Generation], [CooGAN], [Knowledge Style Transfer], [SimSwap].