Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape

TL;DR

VividTalker is a novel framework that generates realistic speech-driven 3D facial animations with natural head poses and detailed facial features by disentangling and separately modeling mouth movements and head poses using a Transformer-based approach.

Contribution

It introduces a new method for disentangling facial attributes and synthesizing detailed 3D facial shapes, addressing data scarcity and controllability issues in speech-driven animation.

Findings

Outperforms existing methods in realism and expressiveness

Successfully models natural head poses and facial details

Creates a new detailed 3D facial shape dataset

Abstract

The creation of lifelike speech-driven 3D facial animation requires a natural and precise synchronization between audio input and facial expressions. However, existing works still fail to render shapes with flexible head poses and natural facial details (e.g., wrinkles). This limitation is mainly due to two aspects: 1) Collecting training set with detailed 3D facial shapes is highly expensive. This scarcity of detailed shape annotations hinders the training of models with expressive facial animation. 2) Compared to mouth movement, the head pose is much less correlated to speech content. Consequently, concurrent modeling of both mouth movement and head pose yields the lack of facial movement controllability. To address these challenges, we introduce VividTalker, a new framework designed to facilitate speech-driven 3D facial animation characterized by flexible head pose and natural facial details. Specifically, we explicitly disentangle facial animation into head pose and mouth movement and encode them separately into discrete latent spaces. Then, these attributes are generated through an autoregressive process leveraging a window-based Transformer architecture. To augment the richness of 3D facial animation, we construct a new 3D dataset with detailed shapes and learn to synthesize facial details in line with speech content. Extensive quantitative and qualitative experiments demonstrate that VividTalker outperforms state-of-the-art methods, resulting in vivid and realistic speech-driven 3D facial animation.