Learning to Estimate 3D Human Pose from Point Cloud
This addresses the problem of 3D human pose estimation for computer vision applications, representing an incremental improvement by applying a novel input type to an existing task.
The paper tackles 3D human pose estimation by proposing a deep network that uses point cloud data from depth images instead of conventional CNN-based methods, achieving higher accuracy than previous state-of-the-art methods on ITOP and EVAL datasets.
3D pose estimation is a challenging problem in computer vision. Most of the existing neural-network-based approaches address color or depth images through convolution networks (CNNs). In this paper, we study the task of 3D human pose estimation from depth images. Different from the existing CNN-based human pose estimation method, we propose a deep human pose network for 3D pose estimation by taking the point cloud data as input data to model the surface of complex human structures. We first cast the 3D human pose estimation from 2D depth images to 3D point clouds and directly predict the 3D joint position. Our experiments on two public datasets show that our approach achieves higher accuracy than previous state-of-art methods. The reported results on both ITOP and EVAL datasets demonstrate the effectiveness of our method on the targeted tasks.