# Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face

## TL;DR

This paper introduces a deterministic conditional GAN that translates depth face data into plausible RGB images, enabling face recognition tasks even when RGB images are unavailable or difficult to acquire.

## Contribution

The paper presents a novel depth-to-RGB face translation method using a deterministic conditional GAN trained on RGB-D datasets, improving over previous approaches.

## Key findings

- Generated faces are plausible and useful for recognition tasks.
- Depth data can substitute RGB images in challenging lighting conditions.
- The approach outperforms previous domain translation methods.

## Abstract

Can faces acquired by low-cost depth sensors be useful to catch some characteristic details of the face? Typically the answer is no. However, new deep architectures can generate RGB images from data acquired in a different modality, such as depth data. In this paper, we propose a new \textit{Deterministic Conditional GAN}, trained on annotated RGB-D face datasets, effective for a face-to-face translation from depth to RGB. Although the network cannot reconstruct the exact somatic features for unknown individual faces, it is capable to reconstruct plausible faces; their appearance is accurate enough to be used in many pattern recognition tasks. In fact, we test the network capability to hallucinate with some \textit{Perceptual Probes}, as for instance face aspect classification or landmark detection. Depth face can be used in spite of the correspondent RGB images, that often are not available due to difficult luminance conditions. Experimental results are very promising and are as far as better than previously proposed approaches: this domain translation can constitute a new way to exploit depth data in new future applications.