ROOT=/path/to/object-deformnet
cd $ROOT/lib/nn_distance
python setup.py install --user

data
├── CAMERA
│   ├── train
│   └── val
├── Real
│   ├── train
│   └── test
├── gts
│   ├── val
│   └── real_test
└── obj_models
    ├── train
    ├── val
    ├── real_train
    └── real_test

results
├── mrcnn_results
│   ├── real_test
│   └── val
└── nocs_results
    ├── real_test
    └── test

# train: python train.py

# test: python evaluate.py

@inproceedings{wang2021category,
  title={Category-level 6d object pose estimation via cascaded relation and recurrent reconstruction networks},
  author={Wang, Jiaze and Chen, Kai and Dou, Qi},
  booktitle={2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages={4807--4814},
  year={2021},
  organization={IEEE}
}

@inproceedings{chen2021sgpa,
  title={Sgpa: Structure-guided prior adaptation for category-level 6d object pose estimation},
  author={Chen, Kai and Dou, Qi},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={2773--2782},
  year={2021}
}