Facial Expression Editing with Continuous Emotion Labels

Abstract

Recently deep generative models have achieved impressive results in the field of automated facial expression editing. However, the approaches presented so far presume a discrete representation of human emotions and are therefore limited in the modelling of non-discrete emotional expressions. To overcome this limitation, we explore how continuous emotion representations can be used to control automated expression editing. We propose a deep generative model that can be used to manipulate facial expressions in facial images according to continuous two-dimensional emotion labels. One dimension represents an emotion's valence, the other represents its degree of arousal. We demonstrate the functionality of our model with a quantitative analysis using classifier networks as well as with a qualitative analysis.

8 pages, 5 figures. 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), May 2019

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ExprGAN: Facial Expression Editing with Controllable Expression Intensity
• Semantic Facial Expression Editing using Autoencoded Flow

Cited by in corpus (1)

• All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network