conda create -n cmr python=3
conda activate cmr
conda install pytorch torchvision -c pytorch
pip install -r requirements.txt

export CUDA_HOME=/path/to/cuda/ 

python setup.py install # install to sys.path
python setup.py build develop # install to workspace

cd misc && wget https://people.eecs.berkeley.edu/~kanazawa/cachedir/cmr/model.tar.gz && tar -vzxf model.tar.gz && cd ..

python demo.py --name bird_net --num_train_epoch 500 --img_path misc/demo_data/img1.jpg
python demo.py --name bird_net --num_train_epoch 500 --img_path misc/demo_data/birdie.jpg

@inProceedings{cmrKanazawa18,
  title={Learning Category-Specific Mesh Reconstruction
  from Image Collections},
  author = {Angjoo Kanazawa and
  Shubham Tulsiani
  and Alexei A. Efros
  and Jitendra Malik},
  booktitle={ECCV},
  year={2018}
}
@InProceedings{kato2018renderer
    title={Neural 3D Mesh Renderer},
    author={Kato, Hiroharu and Ushiku, Yoshitaka and Harada, Tatsuya},
    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2018}
}