When Words Smile: Generating Diverse Emotional Facial Expressions from Text
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912660225785856 |
|---|---|
| author | Xu, Haidong Zhang, Meishan Ju, Hao Zheng, Zhedong Cambria, Erik Zhang, Min Fei, Hao |
| author_facet | Xu, Haidong Zhang, Meishan Ju, Hao Zheng, Zhedong Cambria, Erik Zhang, Min Fei, Hao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02508 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | When Words Smile: Generating Diverse Emotional Facial Expressions from Text Xu, Haidong Zhang, Meishan Ju, Hao Zheng, Zhedong Cambria, Erik Zhang, Min Fei, Hao Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | When Words Smile: Generating Diverse Emotional Facial Expressions from Text |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.02508 |