Existing 3D human pose estimators suffer poor generalization performance to new datasets, largely due to the limited diversity of 2D-3D pose pairs in the training data. To address this problem, we present PoseAug, a new auto-augmentation framework that learns to augment the available training poses towards a greater diversity and thus improve generalization of the trained 2D-to-3D pose estimator. Specifically, PoseAug introduces a novel pose augmentor that learns to adjust various geometry factors (e.g., posture, body size, view point and position) of a pose through differentiable operations. With such differentiable capacity, the augmentor can be jointly optimized with the 3D pose estimator and take the estimation error as feedback to generate more diverse and harder poses in an online manner. Moreover, PoseAug introduces a novel part-aware Kinematic Chain Space for evaluating local joint-angle plausibility and develops a discriminative module accordingly to ensure the plausibility of the augmented poses. These elaborate designs enable PoseAug to generate more diverse yet plausible poses than existing offline augmentation methods, and thus yield better generalization of the pose estimator. PoseAug is generic and easy to be applied to various 3D pose estimators. Extensive experiments demonstrate that PoseAug brings clear improvements on both intra-scenario and cross-scenario datasets. Notably, it achieves 88.6% 3D PCK on MPI-INF-3DHP under cross-dataset evaluation setup, improving upon the previous best data augmentation based method by 9.1%. Code can be found at: https://github.com/jfzhang95/PoseAug.

中文翻译：

---

PoseAug：用于3D人类姿势估计的可微分姿势增强框架

现有的3D人体姿势估计器对新数据集的综合性能较差，这主要是由于训练数据中2D-3D姿势对的多样性有限。为了解决这个问题，我们提出了PoseAug，这是一个新的自动增强框架，可以学习将可用的训练姿势增加到更大的多样性，从而提高训练后的2D到3D姿势估计器的通用性。具体而言，PoseAug引入了一种新颖的姿势增强器，该姿势增强器学习通过可微分的操作来调整姿势的各种几何因素（例如，姿势，身体大小，视点和位置）。具有这种可区分的能力，可以将增强器与3D姿态估计器一起进行优化，并将估计误差作为反馈，以在线方式生成更多样和更难的姿势。而且，PoseAug引入了一种新颖的零件感知运动链空间，用于评估局部关节角度的合理性，并相应地开发了一个判别模块，以确保增强姿势的合理性。与现有的离线增强方法相比，这些精心设计的功能使PoseAug可以生成更多种多样但似乎合理的姿势，从而可以更好地概括姿势估计器。PoseAug是通用的，易于应用于各种3D姿态估计器。大量实验表明，PoseAug对场景内和跨场景数据集都带来了明显的改进。值得注意的是，在跨数据集评估设置下，它在MPI-INF-3DHP上达到了88.6％的3D PCK，比以前基于最佳数据增强的方法提高了9.1％。可以在以下网址找到代码：https：//github.com/jfzhang95/PoseAug。