1. Beijing Institute for General Artificial Intelligence 2. Peking University
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
@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}
}