Learning to Generate Facial Depth Maps
This work addresses the challenge of facial depth estimation for applications like face verification, but it is incremental as it builds on existing image-to-image and adversarial training methods.
The paper tackles the problem of estimating facial depth maps from monocular intensity images by proposing a conditional Generative Adversarial Network that combines supervised learning and adversarial training. The result is a model that generates high-quality synthetic depth images, as demonstrated on the Biwi and Pandora datasets, and effectively predicts distinctive facial details for face verification tasks.
In this paper, an adversarial architecture for facial depth map estimation from monocular intensity images is presented. By following an image-to-image approach, we combine the advantages of supervised learning and adversarial training, proposing a conditional Generative Adversarial Network that effectively learns to translate intensity face images into the corresponding depth maps. Two public datasets, namely Biwi database and Pandora dataset, are exploited to demonstrate that the proposed model generates high-quality synthetic depth images, both in terms of visual appearance and informative content. Furthermore, we show that the model is capable of predicting distinctive facial details by testing the generated depth maps through a deep model trained on authentic depth maps for the face verification task.