Learning to Generate Facial Depth Maps

TL;DR

This paper introduces a novel adversarial network architecture that converts monocular face images into accurate depth maps, enhancing facial detail prediction for verification tasks.

Contribution

It presents a conditional GAN framework for depth map estimation from single images, combining supervised and adversarial learning for improved quality.

Findings

Generates high-quality depth maps visually similar to real data

Captures detailed facial features for verification

Effective on public face datasets

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.