3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological constraints for end joints at the part level. Further considering the hierarchy of the human topology, joint-level and body-level dependencies are captured via graph convolutional networks and self-attentions, respectively. Based on these designs, we propose a novel Human Topology aware Network (HTNet), which adopts a channel-split progressive strategy to sequentially learn the structural priors of the human topology from multiple semantic levels: joint, part, and body. Extensive experiments show that the proposed method improves the estimation accuracy by 18.7% on the end joints of limbs and achieves state-of-the-art results on Human3.6M and MPI-INF-3DHP datasets. Code is available at https://github.com/vefalun/HTNet.

翻译：3D 人体构成估计误差会沿着人体的表层传播,并在四肢的端关节积累。在自动控制系统中的回溯跟踪机制的启发下,我们设计了一个内部节点模块,将父节点用作参考,为端关节部分一级建立地形限制。进一步考虑人类地形的等级,通过图示革命网络和自我意识分别收集联合层次和身体层面的依附关系。根据这些设计,我们提议建立一个新的人类地形意识网络(HTNet),采用通道-分流渐进式战略,从多个语义层面(联合、部分和体)连续学习人类地形结构前科。广泛的实验表明,拟议方法提高了对肢体端关节的18.7%的估计准确度,并实现了人类3.6M和MPI-INF-3DHP数据集的状态-艺术结果。代码见https://github.com/vefalun/HTNet。