[TPAMI 2025] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

If you like our project, please give us a star ⭐ on GitHub for the latest update.

Paper Abstract

Recent advances in Text-to-Video generation (T2V) have achieved remarkable success in synthesizing high-quality general videos from textual descriptions. A largely overlooked problem in T2V is that existing models have not adequately encoded physical knowledge of the real world, thus generated videos tend to have limited motion and poor variations. In this paper, we propose \textbf{MagicTime}, a metamorphic time-lapse video generation model, which learns real-world physics knowledge from time-lapse videos and implements metamorphic generation. First, we design a MagicAdapter scheme to decouple spatial and temporal training, encode more physical knowledge from metamorphic videos, and transform pre-trained T2V models to generate metamorphic videos. Second, we introduce a Dynamic Frames Extraction strategy to adapt to metamorphic time-lapse videos, which have a wider variation range and cover dramatic object metamorphic processes, thus embodying more physical knowledge than general videos. Finally, we introduce a Magic Text-Encoder to improve the understanding of metamorphic video prompts. Furthermore, we create a time-lapse video-text dataset called \textbf{ChronoMagic}, specifically curated to unlock the metamorphic video generation ability. Extensive experiments demonstrate the superiority and effectiveness of MagicTime for generating high-quality and dynamic metamorphic videos, suggesting time-lapse video generation is a promising path toward building metamorphic simulators of the physical world.

πŸ’‘ Description

✏️ Citation

If you find our paper and code useful in your research, please consider giving a star and citation.

@article{yuan2025magictime,
  title={Magictime: Time-lapse video generation models as metamorphic simulators},
  author={Yuan, Shenghai and Huang, Jinfa and Shi, Yujun and Xu, Yongqi and Zhu, Ruijie and Lin, Bin and Cheng, Xinhua and Yuan, Li and Luo, Jiebo},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2025},
  publisher={IEEE}
}
Downloads last month
0
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Dataset used to train BestWishYsh/MagicTime

Space using BestWishYsh/MagicTime 1

Collection including BestWishYsh/MagicTime