论文标题
DH-aug：DH前进运动学模型驱动的增强，用于3D人姿势估计
DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation
论文作者
论文摘要
由于数据集的多样性，姿势估计量的概括能力很差。为了解决这个问题，我们通过DH向前运动学模型提出了姿势增强解决方案，我们称之为DH-AUG。我们观察到，以前的工作都是基于单帧姿势增强的，如果将其直接应用于视频姿势估计器，则将存在一些先前忽略的问题：（i）骨旋转的角度歧义（多个解决方案）； （ii）生成的骨骼视频缺乏运动连续性。为了解决这些问题，我们提出了一个基于DH向前运动学模型的特殊发电机，该模型称为DH生成器。广泛的实验表明，DH-AUG可以大大提高视频姿势估计器的概括能力。另外，当应用于单帧3D姿势估计器时，我们的方法的表现优于先前的最佳姿势增强方法。源代码已在https://github.com/hlz0606/dh-aug-dh-forward-kinematics-model-driven-driven-for-for-3d-human pose-pose-pose-估计中发布。
Due to the lack of diversity of datasets, the generalization ability of the pose estimator is poor. To solve this problem, we propose a pose augmentation solution via DH forward kinematics model, which we call DH-AUG. We observe that the previous work is all based on single-frame pose augmentation, if it is directly applied to video pose estimator, there will be several previously ignored problems: (i) angle ambiguity in bone rotation (multiple solutions); (ii) the generated skeleton video lacks movement continuity. To solve these problems, we propose a special generator based on DH forward kinematics model, which is called DH-generator. Extensive experiments demonstrate that DH-AUG can greatly increase the generalization ability of the video pose estimator. In addition, when applied to a single-frame 3D pose estimator, our method outperforms the previous best pose augmentation method. The source code has been released at https://github.com/hlz0606/DH-AUG-DH-Forward-Kinematics-Model-Driven-Augmentation-for-3D-Human-Pose-Estimation.
