This repository includes source code, pretrained model and a testset of paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model", http://arxiv.org/abs/2004.09190.
- The testset are enlarged.
- The source code, pretrained model and some data from testset are released.
If you want to do some comparison with our method, you can download a testset here Google Drive, or Baidu Drive with password: 4nvs. It includes 2D caricatures, groundtruth 68 landmarks, 68 landmarks detected by our method and 3D meshes recovered by our method.
- Python 3.7
- Pytorch 1.4.0
- opencv-python 3.4.2
Clone this repository:
git clone [email protected]:Juyong/CaricatureFace.git
cd CaricatureFace
Install dependencies using Anaconda:
conda create -n cariface python=3.7
source activate cariface
pip install -r requirements.txt
Prepare related data:
- You can download related data for alogorithm here Google Drive, or Baidu Drive with password: tjps.
- Unzip downloaded files and move files into
./data
directory.
Prepare pretrained model:
- You can download pretrained model here Google Drive, or Baidu Drive with password: fukf.
- Unzip downloaded files and move files into
./model
directory.
Prepare some examples:
- You can download some examples here Google Drive, or Baidu Drive with password: unud.
- Unzip downloaded files and move files into
./exp
directory.
Within ./CaricatureFace
directory, run following command:
bash test.sh
Note: Input images must be preprocessed - crop the whole face roughly and resize to size (224, 224).
Firstly, prepare a training set. Then within ./CaricatureFace
directory, run following command:
python train.py --no_premodel
If you find this useful for your research, please cite the paper.