TL;DR该论文提出了一种基于摄像机中心坐标系的神经网络,可以在单个步骤中预测关节位置,取得了当前最先进的结果,适用于 3D 人体姿势估计和 MuPoTS-3D 数据集。
Abstract
The common approach to 3d human pose estimation is predicting the body joint
coordinates relative to the hip. This works well for a single person but is
insufficient in the case of multiple interacting people. Methods predicting
absolute coordinates first estimate a root-relative pose