Double chain networks for monocular 3D human pose estimation

作者：

Highlights：

• The equipotential-joints connection mode to extract the constraint relationships between human equipotential-joints.

• The DCN can effectively extract and combine the global and local constraints of human joints.

• The DCN achieves state-of-the-art performance and exhibits strong generalization ability.

• We apply the DCN to the posture construction of 3D virtual characters.

摘要

•The equipotential-joints connection mode to extract the constraint relationships between human equipotential-joints.•The DCN can effectively extract and combine the global and local constraints of human joints.•The DCN achieves state-of-the-art performance and exhibits strong generalization ability.•We apply the DCN to the posture construction of 3D virtual characters.

论文关键词：3D human pose estimation,Global constraint,Local constraint,Equipotential-joints

论文评审过程：Received 23 January 2022, Revised 6 April 2022, Accepted 11 April 2022, Available online 19 April 2022, Version of Record 3 May 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104452