/gsps

Official implementation for the paper: Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Primary LanguagePythonMIT LicenseMIT

Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Loading GSPS Overview

This is official implementation for the paper

Generating Smooth Pose Sequences for Diverse Human Motion Prediction. In ICCV 21.

Wei Mao, Miaomiao Liu, Mathieu Salzmann.

[paper] [talk]

Dependencies

  • Python >= 3.8
  • PyTorch >= 1.8
  • Tensorboard

tested on pytorch == 1.8.1

Datasets

  • We follow the data preprocessing steps (DATASETS.md) inside the VideoPose3D repo.
  • Given the processed dataset, we further compute the multi-modal future for each motion sequence. All data needed can be downloaded from Google Drive and place all the dataset in data folder inside the root of this repo.

Training and Evaluation

  • We provide 4 YAML configs inside motion_pred/cfg: [dataset].yml and [dataset]_nf.yml for training generator and normalizing flow respectively. These configs correspond to pretrained models inside results.
  • The training and evaluation command is included in run.sh file.

Citing

If you use our code, please cite our work

@inproceedings{mao2021generating,
  title={Generating Smooth Pose Sequences for Diverse Human Motion Prediction},
  author={Mao, Wei and Liu, Miaomiao and Salzmann, Mathieu},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={13309--13318},
  year={2021}
}

Acknowledgments

The overall code framework (dataloading, training, testing etc.) is adapted from DLow.

Licence

MIT