Real time image animation in opencv using first order model

  • 时间: 2020-05-27 08:22:07

Real time Image Animation

The Project is real time application in opencv using first order model

Steps to setup

Step 1: Create virtual environment

create virual environment: pip install virtualenv

activate virtual environment: virtualenv env

Step 2: Activate virtual environment

For windows: env/Script/activate

For Linux: source env/bin/activate

Step 3 : Install required modules

Install modules: pip install -r requirements.txt

Install pytorch and torchvision: pip install torch===1.0.0 torchvision===0.2.1 -f

Step 4 : Download cascade file ,weights and model and save in folder named extract

gdown --id 1wCzJP1XJNB04vEORZvPjNz6drkXm5AUK

On Linux machine: unzip

If on windows platfrom unzip using unzipping software like 7zip.

Delete zip file: rm

Step 5 : Run the project

Run application from live camera: python -i path_to_input_file -c path_to_checkpoint

Example: python .\ -i .\Inputs\Monalisa.png -c .\checkpoints\vox-cpk.pth.tar

Run application from video file: python -i path_to_input_file -c path_to_checkpoint -v path_to_video_file

Example: python .\ -i .\Inputs\Monalisa.png -c .\checkpoints\vox-cpk.pth.tar -v .\video_input\test1.mp4


Tkinter version

Need work on face alignments

Future plans adding deepfake voice and merging with video


@InProceedings{Siarohin_2019_NeurIPS,  author={Siarohin, Aliaksandr and Lathuilière, Stéphane and Tulyakov, Sergey and Ricci, Elisa and Sebe, Nicu},  title={First Order Motion Model for Image Animation},  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},  month = {December},  year = {2019},  url = {}}