InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910040248549376 |
|---|---|
| author | Elmoghany, Mohamed Zhao, Liangbing Shen, Xiaoqian Mukherjee, Subhojyoti Zhou, Yang Wu, Gang Lai, Viet Dac Yoon, Seunghyun Rossi, Ryan Rashwan, Abdullah Mathur, Puneet Manjunatha, Varun Dangi, Daksh Nguyen, Chien Lipka, Nedim Bui, Trung Singh, Krishna Kumar Zhang, Ruiyi Huang, Xiaolei Cho, Jaemin Wang, Yu Park, Namyong Tu, Zhengzhong Chen, Hongjie Eldardiry, Hoda Ahmed, Nesreen Nguyen, Thien Manocha, Dinesh Elhoseiny, Mohamed Dernoncourt, Franck |
| author_facet | Elmoghany, Mohamed Zhao, Liangbing Shen, Xiaoqian Mukherjee, Subhojyoti Zhou, Yang Wu, Gang Lai, Viet Dac Yoon, Seunghyun Rossi, Ryan Rashwan, Abdullah Mathur, Puneet Manjunatha, Varun Dangi, Daksh Nguyen, Chien Lipka, Nedim Bui, Trung Singh, Krishna Kumar Zhang, Ruiyi Huang, Xiaolei Cho, Jaemin Wang, Yu Park, Namyong Tu, Zhengzhong Chen, Hongjie Eldardiry, Hoda Ahmed, Nesreen Nguyen, Thien Manocha, Dinesh Elhoseiny, Mohamed Dernoncourt, Franck |
| contents | Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03646 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions Elmoghany, Mohamed Zhao, Liangbing Shen, Xiaoqian Mukherjee, Subhojyoti Zhou, Yang Wu, Gang Lai, Viet Dac Yoon, Seunghyun Rossi, Ryan Rashwan, Abdullah Mathur, Puneet Manjunatha, Varun Dangi, Daksh Nguyen, Chien Lipka, Nedim Bui, Trung Singh, Krishna Kumar Zhang, Ruiyi Huang, Xiaolei Cho, Jaemin Wang, Yu Park, Namyong Tu, Zhengzhong Chen, Hongjie Eldardiry, Hoda Ahmed, Nesreen Nguyen, Thien Manocha, Dinesh Elhoseiny, Mohamed Dernoncourt, Franck Computer Vision and Pattern Recognition Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence. |
| title | InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03646 |