论文标题
直观且无约束的2D立方体表示，用于同时进行头部检测和姿势估计
An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation
论文作者
论文摘要
最新的头部姿势估计（HPE）方法由Euler角度表示主导。为了避免旋转标签的固有歧义问题，引入了基于季节的替代和基于矢量的表示。但是，它们都不是视觉直觉的，并且通常来自模棱两可的欧拉角标签。在本文中，我们通过{\ it Intuitive}和{\ IT不受约束的} 2D立方体表示，以进行关节头检测和姿势估计。 2D Cube是大约围绕一个头部的3D常规六角形标签的正交投影，其本身包含头部位置。它可以以任何旋转角度直接和明确地反映头部方向。与一般的6-DOF物体姿势估计不同，我们的2D立方体忽略了头部大小的3-DOF，但保留了头部姿势的3-DOF。基于相等的侧长的先前，我们可以从预测的2D头立方体中毫不费力地获得Euler角的闭合溶液，而不是应用容易发生的PNP算法。在实验中，我们提出的方法与公共AFLW2000和BIWI数据集的其他代表性方法取得了可比的结果。此外，对CMU Panoptic数据集的新型测试表明，我们的方法可以无缝地适应不受约束的全视图HPE任务而无需修改。
Most recent head pose estimation (HPE) methods are dominated by the Euler angle representation. To avoid its inherent ambiguity problem of rotation labels, alternative quaternion-based and vector-based representations are introduced. However, they both are not visually intuitive, and often derived from equivocal Euler angle labels. In this paper, we present a novel single-stage keypoint-based method via an {\it intuitive} and {\it unconstrained} 2D cube representation for joint head detection and pose estimation. The 2D cube is an orthogonal projection of the 3D regular hexahedron label roughly surrounding one head, and itself contains the head location. It can reflect the head orientation straightforwardly and unambiguously in any rotation angle. Unlike the general 6-DoF object pose estimation, our 2D cube ignores the 3-DoF of head size but retains the 3-DoF of head pose. Based on the prior of equal side length, we can effortlessly obtain the closed-form solution of Euler angles from predicted 2D head cube instead of applying the error-prone PnP algorithm. In experiments, our proposed method achieves comparable results with other representative methods on the public AFLW2000 and BIWI datasets. Besides, a novel test on the CMU panoptic dataset shows that our method can be seamlessly adapted to the unconstrained full-view HPE task without modification.
