FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks

(1, 2) , (1) , (1) , (2, 3) , (1)
1
2
3

Abstract

In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. We propose a first adaptation of image-toimage translation networks, that have successfully been used in the 2D domain, to 3D face geometry. Leveraging recently released large face scan databases, a neural network has been trained to decouple factors of variations with a better knowledge of the face, enabling facial expressions transfer and neutralization of expressive faces. Specifically, we design an adversarial architecture adapting the base architecture of FUNIT and using SpiralNet++ for our convolutional and sampling operations. Using two publicly available datasets (FaceScape and CoMA), FaceTuneGAN has a better identity decomposition and face neutralization than state-of-the-art techniques. It also outperforms classical deformation transfer approach by predicting blendshapes closer to ground-truth data and with less of undesired artifacts due to too different facial morphologies between source and target.
Fichier principal
Vignette du fichier
2112.00532.pdf (29.94 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03462778 , version 1 (02-12-2021)

Identifiers

  • HAL Id : hal-03462778 , version 1

Cite

Nicolas Olivier, Kelian Baert, Fabien Danieau, Franck Multon, Quentin Avril. FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks. 2021. ⟨hal-03462778⟩
55 View
31 Download

Share

Gmail Facebook Twitter LinkedIn More