PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

Code repository for the paper:
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation
Kehong Gong*, Jianfeng Zhang*, Jiashi Feng
CVPR 2021 (oral presentation)
[paper (coming soon)] [project page (coming soon)]

Citation

If you find this code useful for your research, please consider citing the following paper:

@inproceedings{gong2021poseaug,
  title       = {PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation},
  author      = {Gong, Kehong and Zhang, Jianfeng and Feng, Jiashi},
  booktitle   = {CVPR},
  year        = {2021}
}

Acknowledgements

This code uses (SemGCN, SimpleBL, ST-GCN and VPose3D) as backbone. We gratefully appreciate the impact these libraries had on our work. If you use our code, please consider citing the original papers as well.