Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.14333 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915071014207488 |
|---|---|
| author | Hogue, Steven Zhang, Chenxu Tian, Yapeng Guo, Xiaohu |
| author_facet | Hogue, Steven Zhang, Chenxu Tian, Yapeng Guo, Xiaohu |
| contents | Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common latent space. Our experiments demonstrate that the proposed framework not only maintains state-of-the-art co-speech gesture and talking head generation performance but also significantly reduces the number of parameters required. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14333 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters Hogue, Steven Zhang, Chenxu Tian, Yapeng Guo, Xiaohu Computer Vision and Pattern Recognition Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common latent space. Our experiments demonstrate that the proposed framework not only maintains state-of-the-art co-speech gesture and talking head generation performance but also significantly reduces the number of parameters required. |
| title | Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.14333 |