Facial Expression Editing with Continuous Emotion Labels
This work addresses the problem of modeling non-discrete emotional expressions in automated facial editing for applications in computer vision and human-computer interaction, representing an incremental improvement over existing discrete methods.
The paper tackles the limitation of discrete emotion representations in facial expression editing by proposing a deep generative model that uses continuous two-dimensional emotion labels (valence and arousal) to manipulate facial expressions, demonstrating functionality through quantitative and qualitative analyses.
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.