When Words Smile: Generating Diverse Emotional Facial Expressions from Text

TL;DR

This paper presents an end-to-end text-to-expression model that generates diverse, fluid, and emotionally coherent facial expressions from text, supported by a new large-scale dataset, EmoAva.

Contribution

The paper introduces a novel model for generating expressive facial expressions from text and a new high-quality dataset, EmoAva, to support this task.

Findings

Outperforms baseline methods on multiple metrics

Generates diverse and emotionally coherent expressions

Demonstrates effectiveness on EmoAva and existing datasets

Abstract

Enabling digital humans to express rich emotions has significant applications in dialogue systems, gaming, and other interactive scenarios. While recent advances in talking head synthesis have achieved impressive results in lip synchronization, they tend to overlook the rich and dynamic nature of facial expressions. To fill this critical gap, we introduce an end-to-end text-to-expression model that explicitly focuses on emotional dynamics. Our model learns expressive facial variations in a continuous latent space and generates expressions that are diverse, fluid, and emotionally coherent. To support this task, we introduce EmoAva, a large-scale and high-quality dataset containing 15,000 text-3D expression pairs. Extensive experiments on both existing datasets and EmoAva demonstrate that our method significantly outperforms baselines across multiple evaluation metrics, marking a significant advancement in the field.