Emotiongan: Facial Expression Synthesis Based on Pre-Trained Generator

Abstract

Since the Generative Adversarial Networks (GANs) was proposed, researches on image generation attract many scholars’ general attention and good graces. Traditional GANs generate a sample by playing a minimax game between generator and discriminator. In this paper, we propose a new method called EmotionGAN for generating facial expression. Specifically, the inverse of the generator is firstly utilized to establish the mapping between the input and feature vector. Then the Generalized Linear Model (GLM) is used to fit the changing direction of different expressions in the feature space, which provide a linear guidance to the feature vector along the expression axis, and thus spatial distribution consistence with the target feature vector is assured. Finally the generator is applied to reconstruct the facial image of the expression. By controlling the intensity of the feature vector, the generated image can be smoothly changed on a specific expression. Experiments have shown that EmotionGAN can quickly generate face images with arbitrary expressions while ensuring identity information is not changed, and the image attributes are more accurate and the resolution is higher.

Generating non-verbal responses in virtual agent with use of LSTM network

“…In the domain of generative adversarial networks (GANs), Deng et al [17] developed a GANbased network capable of projecting images into a latent space. They then used a Generalized Linear Model (GLM) to capture the directional aspects of various facial expressions.…”

“…In the process of refining the model for optimal performance, an exhaustive exploration of hyperparameter configurations is undertaken. Hyperparameters include every parameter that needs to be defined before training has commenced [17]. The best example of this parameter is the learning rate, without the learning rate specified training is impossible.…”

Explore the Expression: Facial Expression Generation using Auxiliary Classifier Generative Adversarial Network

“…Another similar CNN based approach was reported in [8] and evaluated the model with pre-trained face recognition models [9]. A more GAN related work was reported in [10] in which authors proposed a method which encodes the given image into feature space and then uses a Generalized Linear Model (GLM) to fit the general direction of different facial expressions in the feature space. Another GAN based work was proposed in [11] which uses one generator and three discriminators based architecture and could transform an input image along with an affect condition to another emotion.…”

FExGAN-Meta: Facial Expression Generation with Meta Humans

“…In [10] another CNN based architecture was proposed and evaluated on images of faces and identities were compared using pre-trained face model [3]. In [11] a GAN based network was constructed and which projects the image into latent space and then a Generalized Linear Model (GLM) was used to fit the direction of various facial expressions. A GAN architecture was proposed in [12] which could classify and generate images of a facial expression.…”