In this article, we present the Menpo 2D and Menpo 3D benchmarks, two new datasets for multi-pose 2D and 3D facial landmark localisation and tracking. In contrast to the previous benchmarks such as 300W and 300VW, the proposed benchmarks contain facial images in both semi-frontal and profile pose. We introduce an elaborate semi-automatic methodology for providing high-quality annotations for both the Menpo 2D and Menpo 3D benchmarks. In Menpo 2D benchmark, different visible landmark configurations are designed for semi-frontal and profile faces, thus making the 2D face alignment full-pose. In Menpo 3D benchmark, a united landmark configuration is designed for both semi-frontal and profile faces based on the correspondence with a 3D face model, thus making face alignment not only full-pose but also corresponding to the real-world 3D space. Based on the considerable number of annotated images, we organised Menpo 2D Challenge and Menpo 3D Challenge for face alignment under large pose variations in conjunction with CVPR 2017 and ICCV 2017, respectively. The results of these challenges demonstrate that recent deep learning architectures, when trained with the abundant data, lead to excellent results. We also provide a very simple, yet effective solution, named Cascade Multi-view Hourglass Model, to 2D and 3D face alignment. In our method, we take advantage of all 2D and 3D facial landmark annotations in a joint way. We not only capitalise on the correspondences between the semi-frontal and profile 2D facial landmarks but also employ joint supervision from both 2D and 3D facial landmarks. Finally, we discuss future directions on the topic of face alignment.

中文翻译：

---

用于多姿势 2D 和 3D 面部标志定位和跟踪的 Menpo 基准

在本文中，我们介绍了 Menpo 2D 和 Menpo 3D 基准测试，这是用于多姿势 2D 和 3D 面部标志定位和跟踪的两个新数据集。与之前的基准测试（例如 300W 和 300VW）相比，提议的基准测试包含半正面和侧面姿势的面部图像。我们引入了一种精心设计的半自动方法，用于为 Menpo 2D 和 Menpo 3D 基准测试提供高质量的注释。在 Menpo 2D benchmark 中，针对半正面和侧面人脸设计了不同的可见标志配置，从而使 2D 人脸对齐成为全姿势。在 Menpo 3D benchmark 中，基于与 3D 人脸模型的对应关系，为半正面和侧面人脸设计了统一的地标配置，从而使人脸对齐不仅是全姿势，而且还对应于现实世界的 3D 空间。基于大量带注释的图像，我们分别结合 CVPR 2017 和 ICCV 2017 组织了 Menpo 2D Challenge 和 Menpo 3D Challenge 以在大姿态变化下进行面部对齐。这些挑战的结果表明，最近的深度学习架构在使用丰富的数据进行训练时会产生出色的结果。我们还提供了一个非常简单但有效的解决方案，名为 Cascade Multi-view Hourglass Model，用于 2D 和 3D 人脸对齐。在我们的方法中，我们以联合方式利用所有 2D 和 3D 面部标志注释。我们不仅利用了半正面和侧面 2D 面部标志之间的对应关系，而且还采用了 2D 和 3D 面部标志的联合监督。最后，我们讨论了人脸对齐主题的未来方向。