This is the repository that contains source code for the SViMo website.
- Title: SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios
- TL;DR: A novel framework that combines visual priors and dynamic constraints within a synchronized diffusion process for joint generation of video and motion in Hand-Object Interaction (HOI) scenarios.
- Project page: https://droliven.github.io/SViMo_project/.
- arxiv: https://arxiv.org/abs/2506.02444.
- [PDF].
- HF Paper page: https://huggingface.co/papers/2506.02444.
- Video-Youtube: https://youtu.be/H1ISaXiiKtk.
- Video-Local: static/videos/svimo_video.mp4.
- Poster: static/images/svimo_poster.png.
- Slides: static/pdfs/svimo_slides.pdf.
- Code: https://github.com/Droliven/SViMo_code.
- Models: Coming soon.
- Dataset: Coming soon.
If you find Nerfies useful for your work please cite:
@inproceedings{dang2025svimo,
title={SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios},
author={Dang, Lingwei and Shao, Ruizhi and Zhang, Hongwen and Min, Wei and Liu, Yebin and Wu, Qingyao},
booktitle=NeurIPS,
year={2025}
}
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
