GFPose: Learning 3D Human Pose Prior with Gradient Fields
1. Beijing Institute for General Artificial Intelligence 2. Peking University
GFPose is a score-based 3D human pose prior model that can be easily used for various applications, e.g., 3D human pose estimation, pose denoising and generation. Our key idea is to estimate the gradient field (a.k.a, score) of the perturbed human pose. Scores encode "what a reasonable pose looks like." We can leverage them to adjust poses to be more plausible and feasible to a task specification.
Multi-hypothesis 3D Human Pose Estimation
![](https://www.google.com/images/icons/product/drive-32.png)
Qualitative comparison with cVAE
We compare the hypotheses sampled from GFPose and cVAE[1]. Preds and GTs are colored yellow and white, respectively.
Both methods work well with the easier case (3rd row). However, GFPose performs better with the harder ones (first two rows). It gives more diverse hypotheses while keeping faithful to GT.
[1] Saurabh Sharma, et al. Monocular 3d human pose estimation by generation and ordinal ranking. In ICCV, 2019
Reconstruction from Occluded 2D Observation
![](https://www.google.com/images/icons/product/drive-32.png)
Reconstruction from Partial 3D Observation
![](https://www.google.com/images/icons/product/drive-32.png)
Pose Denoising
![](https://www.google.com/images/icons/product/drive-32.png)
Pose Generation
![](https://www.google.com/images/icons/product/drive-32.png)
Citation
@article{ci2022gfpose,
title = {GFPose: Learning 3D Human Pose Prior with Gradient Fields},
author = {Ci, Hai and Wu, Mingdong and Zhu, Wentao and Ma, Xiaoxuan and Dong, Hao and Zhong, Fangwei and Wang, Yizhou},
journal = {arXiv preprint arXiv:2212.08641},
year = {2022}
}