Awesome

Jittor Implementation for the pepar Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild (CVPR 2020 oral).

Datasets

1. CelebA face dataset. Please download the original images (img_celeba.7z) from their website and run celeba_crop.py in data/ to crop the images.
2. Synthetic face dataset generated using Basel Face Model. This can be downloaded using the script download_synface.sh provided in data/.
3. Cat face dataset composed of Cat Head Dataset and Oxford-IIIT Pet Dataset (license). This can be downloaded using the script download_cat.sh provided in data/.

Please remember to cite the corresponding papers if you use these datasets.

Training

Check the configuration files in experiments/ and run experiments, eg:

git clone https://github.com/Jittor/unsup3d-jittor
cd unsup3d-jittor
bash install.sh
python3.7 run.py --config experiments/train_synface.yml

Testing

Check the configuration files in experiments/ and run experiments, eg:

python3.7 run.py --config experiments/test_synface.yml

Pretrained model

Here we provide our pretrained synface model trained using the default config experiments/train_synface.yml. You can run the following scripts to test Table 2 in the paper.

bash pretrained/download_pretrained_synface.sh
python3.7 run.py --config experiments/test_synface.yml

The following is SIDE and MAD compared with original paper (Table 2).

Citation

@InProceedings{Wu_2020_CVPR,
  author = {Shangzhe Wu and Christian Rupprecht and Andrea Vedaldi},
  title = {Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild},
  booktitle = {CVPR},
  year = {2020}
}