Compositional Human Pose Regression
Compositional Human Pose Regression
复制标题
DOI：
10.1016/j.cviu.2018.10.006
复制
发表时间：
2018-11-01
影响因子：
4.5
通讯作者：
Wei, Yichen
中科院分区：
文献类型：
--
作者：
Liang, Shuang;Sun, Xiao;Wei, Yichen
基于回归的方法在人体姿势估计方面的性能不如基于检测的方法。一个核心问题是，姿势中的结构信息在之前的回归方法中没有得到很好的利用。在这项工作中，我们提出了一种结构感知回归方法。它采用使用骨骼而不是关节的重新参数化姿势表示。它利用关节连接结构来定义组合损失函数，该函数对姿势中的长程交互进行编码。它简单、有效且通用，适用于统一设置中的 2D 和 3D 姿态估计。综合评估验证了我们方法的有效性。它在 Human3.6M 数据集上建立了新的最先进技术。它在 MPII 和 COCO 数据集上也具有竞争力。
Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It establishes the new state-of-the-art on Human3.6M dataset. It is also competitive on MPII and COCO datasets.