UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control
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_ | 1866916543740248064 |
|---|---|
| author | Sun, Wenzhang Li, Xiang Di, Donglin Liang, Zhuding Zhang, Qiyuan Li, Hao Chen, Wei Cui, Jianxun |
| author_facet | Sun, Wenzhang Li, Xiang Di, Donglin Liang, Zhuding Zhang, Qiyuan Li, Hao Chen, Wei Cui, Jianxun |
| contents | Recently, animating portrait images using audio input is a popular task. Creating lifelike talking head videos requires flexible and natural movements, including facial and head dynamics, camera motion, realistic light and shadow effects. Existing methods struggle to offer comprehensive, multifaceted control over these aspects. In this work, we introduce UniAvatar, a designed method that provides extensive control over a wide range of motion and illumination conditions. Specifically, we use the FLAME model to render all motion information onto a single image, maintaining the integrity of 3D motion details while enabling fine-grained, pixel-level control. Beyond motion, this approach also allows for comprehensive global illumination control. We design independent modules to manage both 3D motion and illumination, permitting separate and combined control. Extensive experiments demonstrate that our method outperforms others in both broad-range motion control and lighting control. Additionally, to enhance the diversity of motion and environmental contexts in current datasets, we collect and plan to publicly release two datasets, DH-FaceDrasMvVid-100 and DH-FaceReliVid-200, which capture significant head movements during speech and various lighting scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19860 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control Sun, Wenzhang Li, Xiang Di, Donglin Liang, Zhuding Zhang, Qiyuan Li, Hao Chen, Wei Cui, Jianxun Computer Vision and Pattern Recognition Recently, animating portrait images using audio input is a popular task. Creating lifelike talking head videos requires flexible and natural movements, including facial and head dynamics, camera motion, realistic light and shadow effects. Existing methods struggle to offer comprehensive, multifaceted control over these aspects. In this work, we introduce UniAvatar, a designed method that provides extensive control over a wide range of motion and illumination conditions. Specifically, we use the FLAME model to render all motion information onto a single image, maintaining the integrity of 3D motion details while enabling fine-grained, pixel-level control. Beyond motion, this approach also allows for comprehensive global illumination control. We design independent modules to manage both 3D motion and illumination, permitting separate and combined control. Extensive experiments demonstrate that our method outperforms others in both broad-range motion control and lighting control. Additionally, to enhance the diversity of motion and environmental contexts in current datasets, we collect and plan to publicly release two datasets, DH-FaceDrasMvVid-100 and DH-FaceReliVid-200, which capture significant head movements during speech and various lighting scenarios. |
| title | UniAvatar: Taming Lifelike Audio-Driven Talking Head Generation with Comprehensive Motion and Lighting Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.19860 |