Training accurate 3D human pose estimators requires large amount of 3D
ground-truth data which is costly to collect. Various weakly or self supervised
pose estimation methods have been proposed due to lack of 3D data.
Nevertheless, these methods, in addition to 2D ground-truth poses, require
either additional supervision in various forms (e.g. unpaired 3D ground truth
data, a small subset of labels) or the camera parameters in multiview settings.
To address these problems, we present EpipolarPose, a self-supervised learning
method for 3D human pose estimation, which does not need any 3D ground-truth
data or camera extrinsics. During training, EpipolarPose estimates 2D poses
from multi-view images, and then, utilizes epipolar geometry to obtain a 3D
pose and camera geometry which are subsequently used to train a 3D pose
estimator. We demonstrate the effectiveness of our approach on standard
benchmark datasets i.e. Human3.6M and MPI-INF-3DHP where we set the new
state-of-the-art among weakly/self-supervised methods. Furthermore, we propose
a new performance measure Pose Structure Score (PSS) which is a scale
invariant, structure aware measure to evaluate the structural plausibility of a
pose with respect to its ground truth. Code and pretrained models are available
at this https URL

本研究提出了一种基于自主学习的 3D 人体姿态估计方法 EpipolarPose，可以不需要 3D 地面真实数据或相机外参信息，通过对多视图图像中的 2D 姿态进行估计，然后利用极线几何获得 3D 姿态和相机几何信息进行训练 3D 姿态估计，实验结果表明，在标准数据集 Human3.6M 和 MPI-INF-3DHP 上，本方法 在弱 / 自监督方法中取得了最新的最新最优成果，并提出了一种新的性能度量 Pose Structure Score （PSS） 来度量姿势相对于其地面真实性的结构合理性。