Head pose estimation using deep neural networks and 3D point clouds

作者：

Highlights：

• We propose head pose estimation using deep neural networks and 3D point cloud.

• We adopt 3D point cloud data generated from depth to estimate 3D head pose.

• This is the first work of 3D point cloud based head pose estimation in a deep learning framework.

摘要

•We propose head pose estimation using deep neural networks and 3D point cloud.•We adopt 3D point cloud data generated from depth to estimate 3D head pose.•This is the first work of 3D point cloud based head pose estimation in a deep learning framework.

论文关键词：Head pose estimation,Deep learning,Graph convolution,Multi-layer perceptron,Point cloud

论文评审过程：Received 6 May 2020, Revised 21 July 2021, Accepted 27 July 2021, Available online 28 July 2021, Version of Record 12 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108210