DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929237927133184 |
|---|---|
| author | Ma, Zhiyuan Zhu, Xiangyu Qi, Guojun Qian, Chen Zhang, Zhaoxiang Lei, Zhen |
| author_facet | Ma, Zhiyuan Zhu, Xiangyu Qi, Guojun Qian, Chen Zhang, Zhaoxiang Lei, Zhen |
| contents | Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. However, their mere aggregation does not lead to improved performance. We suspect this is due to a shortage of paired audio-4D data, which is crucial for the Transformer to effectively perform as a denoiser within the Diffusion framework. To tackle this issue, we present DiffSpeaker, a Transformer-based network equipped with novel biased conditional attention modules. These modules serve as substitutes for the traditional self/cross-attention in standard Transformers, incorporating thoughtfully designed biases that steer the attention mechanisms to concentrate on both the relevant task-specific and diffusion-related conditions. We also explore the trade-off between accurate lip synchronization and non-verbal facial expressions within the Diffusion paradigm. Experiments show our model not only achieves state-of-the-art performance on existing benchmarks, but also fast inference speed owing to its ability to generate facial motions in parallel. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05712 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer Ma, Zhiyuan Zhu, Xiangyu Qi, Guojun Qian, Chen Zhang, Zhaoxiang Lei, Zhen Computer Vision and Pattern Recognition Artificial Intelligence Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. However, their mere aggregation does not lead to improved performance. We suspect this is due to a shortage of paired audio-4D data, which is crucial for the Transformer to effectively perform as a denoiser within the Diffusion framework. To tackle this issue, we present DiffSpeaker, a Transformer-based network equipped with novel biased conditional attention modules. These modules serve as substitutes for the traditional self/cross-attention in standard Transformers, incorporating thoughtfully designed biases that steer the attention mechanisms to concentrate on both the relevant task-specific and diffusion-related conditions. We also explore the trade-off between accurate lip synchronization and non-verbal facial expressions within the Diffusion paradigm. Experiments show our model not only achieves state-of-the-art performance on existing benchmarks, but also fast inference speed owing to its ability to generate facial motions in parallel. |
| title | DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.05712 |