MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914115697508352 |
|---|---|
| author | Li, Quanhao Xing, Zhen Wang, Rui Zhang, Hui Dai, Qi Wu, Zuxuan |
| author_facet | Li, Quanhao Xing, Zhen Wang, Rui Zhang, Hui Dai, Qi Wu, Zuxuan |
| contents | Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly defined spatial paths. However, existing methods struggle with complex object movements and multi-object motion control, resulting in imprecise trajectory adherence, poor object consistency, and compromised visual quality. Furthermore, these methods only support trajectory control in a single format, limiting their applicability in diverse scenarios. Additionally, there is no publicly available dataset or benchmark specifically tailored for trajectory-controllable video generation, hindering robust training and systematic evaluation. To address these challenges, we introduce MagicMotion, a novel image-to-video generation framework that enables trajectory control through three levels of conditions from dense to sparse: masks, bounding boxes, and sparse boxes. Given an input image and trajectories, MagicMotion seamlessly animates objects along defined trajectories while maintaining object consistency and visual quality. Furthermore, we present MagicData, a large-scale trajectory-controlled video dataset, along with an automated pipeline for annotation and filtering. We also introduce MagicBench, a comprehensive benchmark that assesses both video quality and trajectory control accuracy across different numbers of objects. Extensive experiments demonstrate that MagicMotion outperforms previous methods across various metrics. Our project page are publicly available at https://quanhaol.github.io/magicmotion-site. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance Li, Quanhao Xing, Zhen Wang, Rui Zhang, Hui Dai, Qi Wu, Zuxuan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to enable precise object motion control through explicitly defined spatial paths. However, existing methods struggle with complex object movements and multi-object motion control, resulting in imprecise trajectory adherence, poor object consistency, and compromised visual quality. Furthermore, these methods only support trajectory control in a single format, limiting their applicability in diverse scenarios. Additionally, there is no publicly available dataset or benchmark specifically tailored for trajectory-controllable video generation, hindering robust training and systematic evaluation. To address these challenges, we introduce MagicMotion, a novel image-to-video generation framework that enables trajectory control through three levels of conditions from dense to sparse: masks, bounding boxes, and sparse boxes. Given an input image and trajectories, MagicMotion seamlessly animates objects along defined trajectories while maintaining object consistency and visual quality. Furthermore, we present MagicData, a large-scale trajectory-controlled video dataset, along with an automated pipeline for annotation and filtering. We also introduce MagicBench, a comprehensive benchmark that assesses both video quality and trajectory control accuracy across different numbers of objects. Extensive experiments demonstrate that MagicMotion outperforms previous methods across various metrics. Our project page are publicly available at https://quanhaol.github.io/magicmotion-site. |
| title | MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia |
| url | https://arxiv.org/abs/2503.16421 |