A deep Coarse-to-Fine network for head pose estimation from synthetic data

作者：

Highlights：

• Estimating head pose with a Coarse-to-Fine neural network.

• The network is achieved by joint learning, and thus are computationally efficient.

• Design a rendering pipeline to synthesize realistic head images with annotations.

• The generated head pose dataset contains 310k images.

摘要

•Estimating head pose with a Coarse-to-Fine neural network.•The network is achieved by joint learning, and thus are computationally efficient.•Design a rendering pipeline to synthesize realistic head images with annotations.•The generated head pose dataset contains 310k images.

论文关键词：Head pose estimation,Coarse-to-Fine,Joint learning

论文评审过程：Received 11 December 2018, Revised 5 May 2019, Accepted 14 May 2019, Available online 21 May 2019, Version of Record 29 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.026