SliderGAN: Synthesizing Expressive Face Images by Sliding 3D Blendshape Parameters

by   Evangelos Ververas, et al.

Image-to-image (i2i) translation is the dense regression problem of learning how to transform an input image into an output using aligned image pairs. Remarkable progress has been made in i2i translation with the advent of Deep Convolutional Neural Networks (DCNNs) and particular using the learning paradigm of Generative Adversarial Networks (GANs). In the absence of paired images, i2i translation is tackled with one or multiple domain transformations (i.e., CycleGAN, StarGAN etc.). In this paper, we study a new problem, that of image-to-image translation, under a set of continuous parameters that correspond to a model describing a physical process. In particular, we propose the SliderGAN which transforms an input face image into a new one according to the continuous values of a statistical blendshape model of facial motion. We show that it is possible to edit a facial image according to expression and speech blendshapes, using sliders that control the continuous values of the blendshape model. This provides much more flexibility in various tasks, including but not limited to face editing, expression transfer and face neutralisation, comparing to models based on discrete expressions or action units.


page 2

page 9

page 10

page 11

page 12

page 14

page 15

page 16


Face Video Generation from a Single Image and Landmarks

In this paper we are concerned with the challenging problem of producing...

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

In this paper, we present FaceTuneGAN, a new 3D face model representatio...

Video-to-Video Translation for Visual Speech Synthesis

Despite remarkable success in image-to-image translation that celebrates...

Learning Continuous Face Representation with Explicit Functions

How to represent a face pattern? While it is presented in a continuous w...

Face Translation between Images and Videos using Identity-aware CycleGAN

This paper presents a new problem of unpaired face translation between i...

Refacing: reconstructing anonymized facial features using GANs

Anonymization of medical images is necessary for protecting the identity...

F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks

Formulated as a conditional generation problem, face animation aims at s...

Please sign up or login with your details

Forgot password? Click here to reset