The goal of image-based 3D head pose estimation is try to estimate the facial direction with 2D images. It is an important attribute widely used in many applications related to faces. However, accurate estimation is hard due to complicated part and pose absence in facial images. Recently, some improvement has been obtained with methods based on neural networks, but most of them ignore the geometric information of facial parts. In this paper, we try to tackle this issue and propose a novel geometry-aware representation. It is based on Stacked Capsule Graph Autoencoders (SCGAE). Different from current methods, we apply Stacked Capsule Autoencoders (SCAE) to encode the parts and poses of facial images. These parts and poses are used to train templates and reconstruct the original faces in decoders. In addition, we improve SCAE with locality loss, in which the inner relationships of similar samples are utilized. To achieve it, graph regularization is applied. In this way, an improved geometry-aware representation can be computed. It is compatible with existing regression methods and experimental results on commonly-used datasets about head pose estimation validate the effectiveness of SCGAE.

基于图像的 3D 头部姿态估计的目标是尝试用 2D 图像估计面部方向。它是许多与人脸相关的应用程序中广泛使用的重要属性。然而，由于面部图像中的复杂部分和姿势缺失，准确估计很困难。最近，基于神经网络的方法取得了一些改进，但大多数都忽略了面部部位的几何信息。在本文中，我们尝试解决这个问题并提出一种新颖的几何感知表示。它基于堆叠胶囊图自动编码器 (SCGAE)。与当前方法不同，我们应用堆叠胶囊自动编码器 (SCAE) 对面部图像的部分和姿势进行编码。这些部分和姿势用于训练模板并在解码器中重建原始人脸。此外，我们通过局部损失改进了 SCAE，其中利用了相似样本的内部关系。为了实现它，应用了图正则化。通过这种方式，可以计算改进的几何感知表示。它与现有的回归方法兼容，并且在有关头部姿势估计的常用数据集上的实验结果验证了 SCGAE 的有效性。