FaceTuneGAN: Face autoencoder for convolutional expression transfer using neural generative adversarial networks

• DOI: 10.1016/j.cag.2022.12.004
• Publication Date: 2022-12-17T15:48:31Z
• Authors: Nicolas Olivier; Kelian Baert; Fabien Danieau; Franck Multon; Quentin Avril
• Keywords: Autoencoder; Expression (computer science); Representation

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-to-image 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.