Modeling vs. learning approaches for monocular 3D human pose estimation
Modeling vs. learning approaches for monocular 3D human pose estimation
复制标题
单眼 3D 人体姿势估计的建模与学习方法
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Jordi Gonzàlez
中科院分区：
文献类型：
--
作者：
Wenjuan Gong;Jürgen Brauer;Michael Arens;Jordi Gonzàlez
我们解决的问题，3D人体姿态估计的基础上，单目图像的2D姿态估计。已经为这项任务提出了大量的方法。他们中的一些人避免明确地建模从2D姿势到3D姿势的映射，而是使用训练样本来学习映射。相反，还存在尝试使用关于2D和3D姿态之间的连接的一些知识来明确地对从2D到3D的映射进行建模的方法。令人惊讶的是，到目前为止，还没有实验比较这两类方法，使用完全相同的数据源，从而雕刻出两种方法的优点和缺点。在本文中，我们提出了这样一个比较最常用的学习方法的3D姿态估计-高斯过程回归-与最常用的建模方法-几何重建的3D姿态。结果表明，当与训练数据相比，视点或动作类型没有大的变化时，基于学习的方法优于建模方法。相比之下，当训练数据和应用数据之间存在较大差异时，建模方法显示出优于学习方法的优势。
We tackle the problem of 3D human pose estimation based on monocular images from which 2D pose estimates are available. A large number of approaches have been proposed for this task. Some of them avoid to model the mapping from 2D poses to 3D poses explicitly but learn the mapping using training samples. In contrast, there also exist methods that try to use some knowledge about the connection between 2D and 3D poses to model the mapping from 2D to 3D explicitly. Surprisingly, up to now there is no experimental comparison of these two classes of approaches that uses exactly the same data sources and thereby carves out the advantages and disadvantages of both methods. In this paper we present such a comparison for the most commonly used learning approach for 3D pose estimation - the Gaussian process regressor - with the most used modeling approach - the geometric reconstruction of 3D poses. The results show that the learning based approach outperforms the modeling approach when there are no big changes in viewpoint or action types compared to the training data. In contrast, modeling approaches show advantages over learning approaches when there are big differences between training and application data.