Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face
This addresses the challenge of using depth data in difficult lighting conditions where RGB images are unavailable, though it is an incremental improvement on existing domain translation methods.
The paper tackles the problem of generating plausible RGB face images from depth sensor data using a new Deterministic Conditional GAN, achieving results that outperform previous approaches and enabling pattern recognition tasks like face classification and landmark detection.
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.