论文标题
6D人姿势估计的方向关键点
Orientation Keypoints for 6D Human Pose Estimation
论文作者
论文摘要
大多数实时人类姿势估计方法基于检测关节位置。使用检测到的关节位置，可以计算四肢的偏航和俯仰。但是，沿肢体的滚动对于体育分析和计算机动画等应用至关重要，因为这种旋转轴仍然没有观察到，因此无法计算。因此，在本文中，我们引入了定向关键，这是一种仅使用单帧RGB图像来估算骨骼接头的完整位置和旋转的新方法。受到运动捕获系统如何使用一组点标记来估计完整骨旋转的启发，我们的方法使用虚拟标记来生成足够的信息，以通过简单的后处理来准确地推断旋转。旋转预测在关节角度最佳报告的平均误差上提高了48％，并且在15个骨旋转中达到93％的精度。该方法还通过MPJPE在原理数据集上测量了联合位置的当前最新结果，并将其概括为野外数据集。
Most realtime human pose estimation approaches are based on detecting joint positions. Using the detected joint positions, the yaw and pitch of the limbs can be computed. However, the roll along the limb, which is critical for application such as sports analysis and computer animation, cannot be computed as this axis of rotation remains unobserved. In this paper we therefore introduce orientation keypoints, a novel approach for estimating the full position and rotation of skeletal joints, using only single-frame RGB images. Inspired by how motion-capture systems use a set of point markers to estimate full bone rotations, our method uses virtual markers to generate sufficient information to accurately infer rotations with simple post processing. The rotation predictions improve upon the best reported mean error for joint angles by 48% and achieves 93% accuracy across 15 bone rotations. The method also improves the current state-of-the-art results for joint positions by 14% as measured by MPJPE on the principle dataset, and generalizes well to in-the-wild datasets.
