This is the official implementation of this paper:
Zhongyu Jiang, Zhuoran Zhou, Lei Li, Wenhao Chai, Cheng-Yen Yang, and Jenq-Neng Hwang. Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation arXiv preprint arXiv:2307.03833 (2023).
Under PA-MPJPE and MPJPE
Methods | CE | Opt | PA-MPJPE ↓ | MPJPE ↓ |
SPIN | 59.2 | 96.9 | ||
VIBE | 51.9 | 82.9 | ||
PARE | 46.4 | 74.7 | ||
HybrIK | 45.0 | 74.1 | ||
HybrIK | ✓ | 50.9 | 82.0 | |
PoseAug | ✓ | 58.5 | 94.1 | |
AdaptPose | ✓ | 46.5 | 81.2 | |
PoseDA | ✓ | 55.3 | 87.7 | |
ZeDO (J=17) | ✓ | ✓ | 42.6 | 80.9 |
ZeDO (J=14) | ✓ | ✓ | 45.4 | 88.6 |
- pytorch >= 1.10
conda create -n ZeDO python==3.9
conda activate ZeDO
pip install -r requirements.txt
Evaluation dataset, clusters and checkpoint: Google Drive
${POSE_ROOT}
|-- configs
|-- lib
|-- run
|-- checkpoint
|-- concatebb
|-- checkpoint_1500.pth
|-- data
|-- h36m
|-- h36m_test.pkl
|-- h36m_sh_dt_ft.pkl
|-- 3dpw
|-- pw3d_test.npz
|-- 3dhp
|-- mpii3d_test.pkl
|-- clusters
|-- 3dhp_cluster1.pkl
|-- h36m_cluster1.pkl
|-- 3dhp_cluster50.pkl
|-- h36m_cluster50.pkl
python -m run.opt_main --config configs/subvp/concat_pose_optimization_<dataset>.py --ckpt_dir ./checkpoint/concatebb --ckpt_name checkpoint_1500.pth --hypo 1 <--gt>
If you find this code useful in your project, please consider citing:
@article{jiang2023back,
title={Back to Optimization: Diffusion-based Zero-Shot 3D Human Pose Estimation},
author={Jiang, Zhongyu and Zhou, Zhuoran and Li, Lei and Chai, Wenhao and Yang, Cheng-Yen and Hwang, Jenq-Neng},
journal={arXiv preprint arXiv:2307.03833},
year={2023}
}
This repo is built on the excellent work score_sde by Yang Song and GFPose by Hai Ci.