Deep 3D human pose estimation: A review

作者：

Highlights：

• The recent methods for deep 3D pose estimation are categorized and thoroughly analyzed.

• Provide an extensive review of related datasets and evaluation metrics.

• Compare the pros and cons of the deep 3D models valuated on the datasets and draw a conclusion.

• We discuss the potential research orientations of future.

摘要

•The recent methods for deep 3D pose estimation are categorized and thoroughly analyzed.•Provide an extensive review of related datasets and evaluation metrics.•Compare the pros and cons of the deep 3D models valuated on the datasets and draw a conclusion.•We discuss the potential research orientations of future.

论文关键词：3D Human Pose Estimation,Deep Learning

论文评审过程：Received 12 August 2020, Revised 13 May 2021, Accepted 14 May 2021, Available online 24 May 2021, Version of Record 9 June 2021.

论文官网地址：https://doi.org/10.1016/j.cviu.2021.103225