论文标题
弱监督的3D人姿势估计中投影模型的误差界限
Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation
论文作者
论文摘要
单眼3D人类姿势估计中最新的最新作品受到弱监督方法的严重影响。这些允许使用2D标签直接从图像中或通过2D到3D姿势提升来学习有效的3D人姿势恢复。在本文中，我们介绍了最常用的简化投影模型的详细分析，该模型将估计的3D姿势表示与2D标签相关联：归一化的透视图和弱视角投影。具体而言，我们在常用的平均每关节位置误差（MPJPE）下得出了这些投影模型的理论下限误差。此外，我们展示了如何更换归一化的透视投影，以避免这种保证的最小误差。我们在最常用的3D人姿势估计基准数据集上评估了派生的下限。我们的结果表明，即使在位置和规模对齐后，这两个投影模型也会导致19.3mm至54.7mm之间的固有最小误差。与最近的最新结果相比，这是相当大的份额。因此，我们的论文建立了一个理论基线，该基线表明在弱监督的3D人类姿势估计中，合适的投影模型的重要性。
The current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods. These allow 2D labels to be used to learn effective 3D human pose recovery either directly from images or via 2D-to-3D pose uplifting. In this paper we present a detailed analysis of the most commonly used simplified projection models, which relate the estimated 3D pose representation to 2D labels: normalized perspective and weak perspective projections. Specifically, we derive theoretical lower bound errors for those projection models under the commonly used mean per-joint position error (MPJPE). Additionally, we show how the normalized perspective projection can be replaced to avoid this guaranteed minimal error. We evaluate the derived lower bounds on the most commonly used 3D human pose estimation benchmark datasets. Our results show that both projection models lead to an inherent minimal error between 19.3mm and 54.7mm, even after alignment in position and scale. This is a considerable share when comparing with recent state-of-the-art results. Our paper thus establishes a theoretical baseline that shows the importance of suitable projection models in weakly supervised 3D human pose estimation.
