EmoFace: Audio-driven Emotional 3D Face Animation

TL;DR

EmoFace is a novel audio-driven method that generates emotionally expressive 3D facial animations with synchronized lip movements, natural eye behaviors, and applicability to MetaHuman models, supported by a new emotional audio-visual dataset.

Contribution

We introduce EmoFace, a new approach for emotional 3D face animation that incorporates emotion-aware encoding, post-processing for realism, and a dedicated dataset for MetaHuman applications.

Findings

Outperforms existing methods in emotional facial animation quality

Successfully generates natural blinks and eye movements

Demonstrates effectiveness in virtual reality and game NPCs

Abstract

Audio-driven emotional 3D face animation aims to generate emotionally expressive talking heads with synchronized lip movements. However, previous research has often overlooked the influence of diverse emotions on facial expressions or proved unsuitable for driving MetaHuman models. In response to this deficiency, we introduce EmoFace, a novel audio-driven methodology for creating facial animations with vivid emotional dynamics. Our approach can generate facial expressions with multiple emotions, and has the ability to generate random yet natural blinks and eye movements, while maintaining accurate lip synchronization. We propose independent speech encoders and emotion encoders to learn the relationship between audio, emotion and corresponding facial controller rigs, and finally map into the sequence of controller values. Additionally, we introduce two post-processing techniques dedicated to enhancing the authenticity of the animation, particularly in blinks and eye movements. Furthermore, recognizing the scarcity of emotional audio-visual data suitable for MetaHuman model manipulation, we contribute an emotional audio-visual dataset and derive control parameters for each frames. Our proposed methodology can be applied in producing dialogues animations of non-playable characters (NPCs) in video games, and driving avatars in virtual reality environments. Our further quantitative and qualitative experiments, as well as an user study comparing with existing researches show that our approach demonstrates superior results in driving 3D facial models. The code and sample data are available at https://github.com/SJTU-Lucy/EmoFace.