HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908607855984640 |
|---|---|
| author | Meng, Yihao Ouyang, Hao Yu, Yue Wang, Qiuyu Wang, Wen Cheng, Ka Leong Wang, Hanlin Li, Yixuan Chen, Cheng Zeng, Yanhong Shen, Yujun Qu, Huamin |
| author_facet | Meng, Yihao Ouyang, Hao Yu, Yue Wang, Qiuyu Wang, Wen Cheng, Ka Leong Wang, Hanlin Li, Yixuan Chen, Cheng Zeng, Yanhong Shen, Yujun Qu, Huamin |
| contents | State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20822 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives Meng, Yihao Ouyang, Hao Yu, Yue Wang, Qiuyu Wang, Wen Cheng, Ka Leong Wang, Hanlin Li, Yixuan Chen, Cheng Zeng, Yanhong Shen, Yujun Qu, Huamin Computer Vision and Pattern Recognition State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/. |
| title | HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.20822 |