Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916769713618944 |
|---|---|
| author | Jin, Xiaoyu Xu, Zunnan Ou, Mingwen Yang, Wenming |
| author_facet | Jin, Xiaoyu Xu, Zunnan Ou, Mingwen Yang, Wenming |
| contents | Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images. Despite advancements, maintaining appearance consistency in animations remains a challenge. Our approach addresses this by introducing a training-free framework that ensures the generated video sequence preserves the reference image's subtleties, such as physique and proportions, through a dual alignment strategy. We decouple skeletal and motion priors from pose information, enabling precise control over animation generation. Our method also improves pixel-level alignment for conditional control from the reference character, enhancing the temporal consistency and visual cohesion of animations. Our method significantly enhances the quality of video generation without the need for large datasets or expensive computational resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16506 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation Jin, Xiaoyu Xu, Zunnan Ou, Mingwen Yang, Wenming Computer Vision and Pattern Recognition Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images. Despite advancements, maintaining appearance consistency in animations remains a challenge. Our approach addresses this by introducing a training-free framework that ensures the generated video sequence preserves the reference image's subtleties, such as physique and proportions, through a dual alignment strategy. We decouple skeletal and motion priors from pose information, enabling precise control over animation generation. Our method also improves pixel-level alignment for conditional control from the reference character, enhancing the temporal consistency and visual cohesion of animations. Our method significantly enhances the quality of video generation without the need for large datasets or expensive computational resources. |
| title | Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.16506 |