We present an unsupervised learning approach to recover 3D human pose from 2D
skeletal joints extracted from a single image. Our method does not require any
multi-view image data, 3D skeletons, correspondences between 2D-3D points, or
use previously learned 3D priors during training. A lifting network accepts 2D
landmarks as inputs and generates a corresponding 3D skeleton estimate. During
training, the recovered 3D skeleton is reprojected on random camera viewpoints
to generate new "synthetic" 2D poses. By lifting the synthetic 2D poses back to
3D and re-projecting them in the original camera view, we can define
self-consistency loss both in 3D and in 2D. The training can thus be self
supervised by exploiting the geometric self-consistency of the
lift-reproject-lift process. We show that self-consistency alone is not
sufficient to generate realistic skeletons, however adding a 2D pose
discriminator enables the lifter to output valid 3D poses. Additionally, to
learn from 2D poses "in the wild", we train an unsupervised 2D domain adapter
network to allow for an expansion of 2D data. This improves results and
demonstrates the usefulness of 2D pose data for unsupervised 3D lifting.
Results on Human3.6M dataset for 3D human pose estimation demonstrate that our
approach improves upon the previous unsupervised methods by 30% and outperforms
many weakly supervised approaches that explicitly use 3D data.

通过采用无监督学习技术，基于来自单个图像的 2D 骨架关节，我们提出了一种恢复 3D 人体姿势的方法，该方法不需要任何多视图图像数据、3D 骨架、2D-3D 点之间的对应关系或在训练过程中使用先前学习的 3D 先验知识。我们的方法采用一个 lifting 网络将 2D 关键点作为输入，并生成相应的 3D 骨架估计，其中我们通过在随机相机视点重投影修复后的 3D 骨架来产生新的 “合成” 2D 姿态。我们还训练了一个 2D 域适配器网络来扩展 2D 数据，并通过自适应正则化机制使域适应效果更好。最终，在 Human3.6M 数据集上，我们的方法对无监督三维 lifting 的改进达到了 30％，并且优于许多明确使用 3D 数据的弱监督方法。