In this demo we propose a coarse to fine reconstruction pipeline, which takes a single RGB image as input and outputs a detailed 3D model of the face. The pipeline is composed by two main blocks, the coarse reconstruction block, which is based on a 3D Morphable Model, and the refinement block, which instead grounds on a Generative Adversarial Network (GAN).

Coarse to Fine 3D Face Reconstruction from Single Image / L. Galteri ; C. Ferrari ; G. Lisanti ; S. Berretti ; A. Del Bimbo. - ELETTRONICO. - (2019), pp. 1-1. (Intervento presentato al convegno IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019) tenutosi a Lille, France nel 14-18 May 2019) [10.1109/FG.2019.8756603].

Coarse to Fine 3D Face Reconstruction from Single Image

L. Galteri;C. Ferrari;G. Lisanti;S. Berretti;A. Del Bimbo
2019

Abstract

In this demo we propose a coarse to fine reconstruction pipeline, which takes a single RGB image as input and outputs a detailed 3D model of the face. The pipeline is composed by two main blocks, the coarse reconstruction block, which is based on a 3D Morphable Model, and the refinement block, which instead grounds on a Generative Adversarial Network (GAN).
2019
IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
Lille, France
14-18 May 2019
L. Galteri ; C. Ferrari ; G. Lisanti ; S. Berretti ; A. Del Bimbo
File in questo prodotto:
File Dimensione Formato  
fg19_demo.pdf

Accesso chiuso

Descrizione: articolo principale
Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: DRM non definito
Dimensione 91.85 kB
Formato Adobe PDF
91.85 kB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1167244
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact