论文标题
6D旋转表示无约束的头部姿势估计
6D Rotation Representation For Unconstrained Head Pose Estimation
论文作者
论文摘要
在本文中，我们提出了一种无约束的端到端头部姿势估计的方法。我们通过为我们的地面真实数据引入旋转矩阵形式主义，并提出连续的6D旋转矩阵表示，以提高旋转矩阵形式，以解决有效且稳健的直接回归。这样，我们的方法可以学习完整的旋转外观，这与以前的方法相反，该方法将姿势预测限制为狭窄的角度以获得令人满意的结果。此外，我们提出了一个基于大地距离的损失，以对SO（3）歧管几何形状惩罚我们的网络。公共AFLW2000和BIWI数据集的实验表明，我们提出的方法极大地比其他最先进的方法高达20 \％。我们开源培训和测试代码以及预先培训的模型：https：//github.com/thohemp/6drepnet。
In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance which is contrary to previous approaches that restrict the pose prediction to a narrow-angle for satisfactory results. In addition, we propose a geodesic distance-based loss to penalize our network with respect to the SO(3) manifold geometry. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20\%. We open-source our training and testing code along with our pre-trained models: https://github.com/thohemp/6DRepNet.
