FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation

Wenbin Teng, Gonglin Chen, Haiwei Chen, Yajie Zhao

University of Southern California

ICCV 2025 🔥

FVGen is a novel approach that accelerates novel-view synthesis by distilling video diffusion models using adversarial training.

teaser_side_by_side.mp4

🚀 News

• [Nov 2025] Code release coming soon!
• [Jun 2025] FVGen accepted to ICCV 2025!

📖 Citation

If you find this work useful, please consider citing:

@inproceedings{teng2025fvgen,
  title={FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation},
  author={Teng, Wenbin and Chen, Gonglin and Chen, Haiwei and Zhao, Yajie},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={26095--26105},
  year={2025}
}

🙏 Acknowledgements

Research was sponsored by the Army Research Office and was accomplished under Cooperative Agreement Numbers W911NF-20-2-0053 and W911NF-25-2-0040. And supported by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior / Interior Business Center (DOI/IBC) contract number 140D0423C0075. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.”