Learning to Generate Facial Depth Maps

Stefano Pini, Filippo Grazioli, Guido Borghi, Roberto Vezzani, Rita Cucchiara
In Proceedings of the 6th international conference on 3D Vision (3DV), 2018
DOI: 10.1109/3DV.2018.00078
Link: Paper

Abstract

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.

@inproceedings{pini2018learning,
  title={Learning to generate facial depth maps},
  author={Pini, Stefano and Grazioli, Filippo and Borghi, Guido and Vezzani, Roberto and Cucchiara, Rita},
  booktitle={2018 International Conference on 3D Vision (3DV)},
  pages={634--642},
  year={2018},
  organization={IEEE}
}