Can faces acquired by low-cost depth sensors be useful to see some characteristic details of the faces? Typically the answer is not. 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 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 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 for darkness of difficult luminance conditions. Experimental results are very promising and are as far as better than previous proposed approaches: this domain translation can constitute a new way to exploit depth data in new future applications.

Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face / Fabbri, Matteo; Borghi, Guido; Lanzi, Fabio; Vezzani, Roberto; Calderara, Simone; Cucchiara, Rita. - (2018). ((Intervento presentato al convegno 24th International Conference on Pattern Recognition (ICPR) 2018 tenutosi a Beijing (China) nel August , 20-24 2018.

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

FABBRI, MATTEO
;
BORGHI, GUIDO;LANZI, FABIO;Roberto Vezzani;Simone Calderara;Rita Cucchiara
2018-01-01

Abstract

Can faces acquired by low-cost depth sensors be useful to see some characteristic details of the faces? Typically the answer is not. 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 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 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 for darkness of difficult luminance conditions. Experimental results are very promising and are as far as better than previous proposed approaches: this domain translation can constitute a new way to exploit depth data in new future applications.
24th International Conference on Pattern Recognition (ICPR) 2018
Beijing (China)
August , 20-24 2018
Fabbri, Matteo; Borghi, Guido; Lanzi, Fabio; Vezzani, Roberto; Calderara, Simone; Cucchiara, Rita
Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face / Fabbri, Matteo; Borghi, Guido; Lanzi, Fabio; Vezzani, Roberto; Calderara, Simone; Cucchiara, Rita. - (2018). ((Intervento presentato al convegno 24th International Conference on Pattern Recognition (ICPR) 2018 tenutosi a Beijing (China) nel August , 20-24 2018.
File in questo prodotto:
File Dimensione Formato  
icpr-2018-domain.pdf

Open access

Tipologia: Versione originale dell'autore proposta per la pubblicazione
Dimensione 2.16 MB
Formato Adobe PDF
2.16 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1159885
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact