M3SVD：Multi-Modal Multi-Scene Video Dataset

@article{TANG2025VideoFusion,
  title={VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration},
  author={Tang, Linfeng and Wang, Yeda and Gong, Meiqi and Li, Zizhuo and Deng, Yuxin and Yi, Xunpeng and Li, Chunyu and Xu, Han and Zhang, Hao and Ma, Jiayi},
  journal={arXiv preprint arXiv:2503.23359},
  year={2025}
}

Scenario Schematic

Visualization of various scenarios in our M3SVD dataset.

Dataset Availability

Note: The current release of the M3SVD dataset includes the test videos. For access to the full dataset, please contact us at linfeng0419@gmail.com. We are happy to collaborate and provide the dataset for research purposes.

Video Demo

Here are some demo videos presented in graphics interchange format (GIF) showcasing our M3SVD dataset:

If our M3SVD dataset is helpful to you, please cite it as：

@article{TANG2025VideoFusion,
  title={VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration},
  author={Tang, Linfeng and Wang, Yeda and Gong, Meiqi and Li, Zizhuo and Deng, Yuxin and Yi, Xunpeng and Li, Chunyu and Xu, Han and Zhang, Hao and Ma, Jiayi},
  journal={arXiv preprint arXiv:2503.23359},
  year={2025}
}