An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation

by   Huayi Zhou, et al.
Shanghai Jiao Tong University
NetEase, Inc

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 intuitive and 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.


page 1

page 2

page 4


A Vector-based Representation to Enhance Head Pose Estimation

This paper proposes to use the three vectors in a rotation matrix as the...

Simultaneous face detection and 360 degree headpose estimation

With many practical applications in human life, including manufacturing ...

6D Rotation Representation For Unconstrained Head Pose Estimation

In this paper, we present a method for unconstrained end-to-end head pos...

HP2IFS: Head Pose estimation exploiting Partitioned Iterated Function Systems

Estimating the actual head orientation from 2D images, with regard to it...

A Simple Baseline for Direct 2D Multi-Person Head Pose Estimation with Full-range Angles

Existing head pose estimation (HPE) mainly focuses on single person with...

Conservative Wasserstein Training for Pose Estimation

This paper targets the task with discrete and periodic class labels (e.g...

Please sign up or login with your details

Forgot password? Click here to reset