Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts
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_ | 1866913263944466432 |
|---|---|
| author | Ma, Yue He, Yingqing Wang, Hongfa Wang, Andong Qi, Chenyang Cai, Chengfei Li, Xiu Li, Zhifeng Shum, Heung-Yeung Liu, Wei Chen, Qifeng |
| author_facet | Ma, Yue He, Yingqing Wang, Hongfa Wang, Andong Qi, Chenyang Cai, Chengfei Li, Xiu Li, Zhifeng Shum, Heung-Yeung Liu, Wei Chen, Qifeng |
| contents | Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to control the movement of different objects or regions. Additionally, current I2V methods require users not only to describe the target motion but also to provide redundant detailed descriptions of frame contents. These two issues hinder the practical utilization of current I2V tools. In this paper, we propose a practical framework, named Follow-Your-Click, to achieve image animation with a simple user click (for specifying what to move) and a short motion prompt (for specifying how to move). Technically, we propose the first-frame masking strategy, which significantly improves the video generation quality, and a motion-augmented module equipped with a short motion prompt dataset to improve the short prompt following abilities of our model. To further control the motion speed, we propose flow-based motion magnitude control to control the speed of target movement more precisely. Our framework has simpler yet precise user control and better generation performance than previous methods. Extensive experiments compared with 7 baselines, including both commercial tools and research methods on 8 metrics, suggest the superiority of our approach. Project Page: https://follow-your-click.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08268 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts Ma, Yue He, Yingqing Wang, Hongfa Wang, Andong Qi, Chenyang Cai, Chengfei Li, Xiu Li, Zhifeng Shum, Heung-Yeung Liu, Wei Chen, Qifeng Computer Vision and Pattern Recognition Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to control the movement of different objects or regions. Additionally, current I2V methods require users not only to describe the target motion but also to provide redundant detailed descriptions of frame contents. These two issues hinder the practical utilization of current I2V tools. In this paper, we propose a practical framework, named Follow-Your-Click, to achieve image animation with a simple user click (for specifying what to move) and a short motion prompt (for specifying how to move). Technically, we propose the first-frame masking strategy, which significantly improves the video generation quality, and a motion-augmented module equipped with a short motion prompt dataset to improve the short prompt following abilities of our model. To further control the motion speed, we propose flow-based motion magnitude control to control the speed of target movement more precisely. Our framework has simpler yet precise user control and better generation performance than previous methods. Extensive experiments compared with 7 baselines, including both commercial tools and research methods on 8 metrics, suggest the superiority of our approach. Project Page: https://follow-your-click.github.io/ |
| title | Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.08268 |