Нема описа

chenxuanhong 72d6436f54 Update README.md пре 4 година
data 01a8d6d0a6 init пре 4 година
doc 83021f155a modify пре 4 година
models 01a8d6d0a6 init пре 4 година
options 01a8d6d0a6 init пре 4 година
util 01a8d6d0a6 init пре 4 година
.gitattributes a0dab0c7b1 Initial commit пре 4 година
.gitignore 01a8d6d0a6 init пре 4 година
LICENSE a0dab0c7b1 Initial commit пре 4 година
README.md 72d6436f54 Update README.md пре 4 година
test_one_image.py 01a8d6d0a6 init пре 4 година
train.py 01a8d6d0a6 init пре 4 година

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, training scripts are coming soon

[Conference paper]

Results

Results1

Video

Dependencies

Usage

Use python3.5, pytorch1.3.0

Use this command to test the face swapping between two images:

python test_one_image.py --isTrain false --name people --Arc_path models/BEST_checkpoint.tar --pic_a_path crop_224/mars.jpg --pic_b_path crop_224/ds.jpg --output_path output/

--name refers to the checkpoint name.

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}
}