We propose to learn a 3D pose estimator by distilling knowledge from
Non-Rigid Structure from Motion (NRSfM). Our method uses solely 2D landmark
annotations. No 3D data, multi-view/temporal footage, or object specific prior
is required. This alleviates the data bottleneck, which is one of the major
concern for supervised methods. The challenge for using NRSfM as teacher is
that they often make poor depth reconstruction when the 2D projections have
strong ambiguity. Directly using those wrong depth as hard target would
negatively impact the student. Instead, we propose a novel loss that ties depth
prediction to the cost function used in NRSfM. This gives the student pose
estimator freedom to reduce depth error by associating with image features.
Validated on H3.6M dataset, our learned 3D pose estimation network achieves
more accurate reconstruction compared to NRSfM methods. It also outperforms
other weakly supervised methods, in spite of using significantly less
supervision.

本研究提出基于非刚性结构运动学 (NRSfM) 知识蒸馏的三维姿态估计方法，它仅使用 2D 地标注释而不需要 3D 数据、多视角 / 时间镜头或对象特定先验，从而减轻了监督方法中的数据瓶颈。该方法使用一种新颖的损失，将深度预测与 NRSfM 中使用的代价函数联系起来，从而使学生姿态估计器能够通过与图像特征关联来减少深度误差。在 H3.6M 数据集上验证，我们学习的三维姿态估计网络实现了比 NRSfM 方法更准确的重建，并且在使用更少的监督的情况下表现比其他弱监督方法更好。