Learning to Estimate 3D Human Pose from Point Cloud

Abstract

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.

References in corpus (4)

• Evaluating and Improving the Depth Accuracy of Kinect for Windows v2
• Towards Good Practices for Deep 3D Hand Pose Estimation
• 3-D Markerless Tracking of Human Gait by Geometric Trilateration of Multiple Kinects
• Development of a Self-Calibrated Motion Capture System by Nonlinear Trilateration of Multiple Kinects v2

Cited by in corpus (1)

• Learning Localization of Body and Finger Animation Skeleton Joints on Three-Dimensional Models of Human Bodies