On the power of data augmentation for head pose estimation

Deep learning has been impressively successful in the last decade in predicting human head poses from monocular images. For in-the-wild inputs, the research community has predominantly relied on a single training set of semi-synthetic nature. This paper suggest the combination of different flavors of synthetic data in order to achieve better generalization to natural images. Moreover, additional expansion of the data volume using traditional out-of-plane rotation synthesis is considered. Together with a novel combination of losses and a network architecture with a standard feature-extractor, a competitive model is obtained, both in accuracy and efficiency, which allows full 6 DoF pose estimation in practical real-time applications.