Tensorflow implementation of the paper "HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences", CVPR 2021.

• Python 3.6
• TensorFlow 2.0
• Tensorflow-Addon
• gin-config
• scikit-learn

pip install -r requirements.txt  --user
pip install gdown

Here we show how to run our code on SMPL intra and inter testing data. You can download the rest of the synthetic SMPL testing data used in the paper here.

bash download_model.sh

(a) Run

mkdir -p ./test_data/

Download our SMPL intra test data from smpl_intra_data in ./test_data/

To evaluate average epe on intra test dataset.

(b) set JOB_NAME="eval_optical_flow_intra" in ./script/inference_local.sh

(c) Run

bash ./script/inference_local.sh

(a) Run

mkdir -p ./test_data/

Download our SMPL inter test data from smpl_inter_data in ./test_data/

To evaluate average epe on inter test dataset.

(b) set JOB_NAME="eval_optical_flow_inter" in ./script/inference_local.sh

(c) Run

bash ./script/inference_local.sh

Currently, we can not provide the whole training dataset due to the copyright and huge size of the data.

Here, we provide an example configuration for training on intra testing data.

bash ./script/train_local.sh

Check out ./inference_demo.ipynb for toy examples.

If you find this code useful in your research, please cite:

@inproceedings{tan2021humangps,
  title = {{HumanGPS: Geodesic PreServing Feature for Dense Human Correspondence}},
  author = {Tan, Feitong and Tang, Danhang and Dou, Mingsong and Guo, Kaiwen and Pandey, Rohit and Keskin, Cem and Du, Ruofei and Sun, Deqing and Bouaziz, Sofien and Fanello, Sean and Tan, Ping and Zhang, Yinda},
  booktitle = {2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
  publisher = {IEEE},
}