Estimating three-dimensional (3-D) human poses from a given two-dimensional (2-D) shape is still an inherently ill-posed problem in computer vision. This paper proposes a method called cascade of multiple neural networks (CMNN) to solve this problem in following two steps: 1) create the initial estimated 3-D shape using the Zhou et al. method with a small number of basis shapes and 2) make this initial shape more alike to the original shape by using the CMNN. In comparing to existing works, the proposed method shows a significant outperformance in both accuracy and processing time. This paper also introduces a new system called Human3D that can estimate the 3-D pose of all people in a single RGB image. This system comprises two part: convolution pose machine (CPM) for estimating 2-D poses of all people in an RGB image and CMNN for reconstructing 3-D poses of them from outputs of the CPM.

中文翻译：

---

使用级联多个神经网络进行 3-D 人体姿势估计


从给定的二维 (2-D) 形状估计三维 (3-D) 人体姿势仍然是计算机视觉中固有的不适定问题。本文提出了一种称为级联多个神经网络（CMNN）的方法，通过以下两个步骤解决这个问题：1）使用 Zhou 等人的方法创建初始估计的 3-D 形状。使用少量基本形状的方法，2）使用 CMNN 使初始形状更类似于原始形状。与现有的工作相比，所提出的方法在准确性和处理时间方面都表现出显着的性能优势。本文还介绍了一种名为 Human3D 的新系统，该系统可以在单个 RGB 图像中估计所有人的 3D 姿势。该系统由两部分组成：卷积姿势机（CPM），用于估计 RGB 图像中所有人的 2-D 姿势；CMNN，用于根据 CPM 的输出重建他们的 3-D 姿势。