Repurposing Pre-Trained Video Diffusion Models for Event-Based Video Interpolation

Abstract

Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, large motion between frames makes this problem ill-posed. Event-based Video Frame Interpolation (EVFI) addresses this challenge by using sparse, high-temporal-resolution event measurements as motion guidance. This guidance allows EVFI methods to significantly outperform frame-only methods. However, to date, EVFI methods have relied upon a limited set of paired event-frame training data, severely limiting their performance and generalization capabilities. In this work, we overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI. We experimentally validate our approach on real-world EVFI datasets, including a new one we introduce. Our method outperforms existing methods and generalizes across cameras far better than existing approaches.

Cite

Text

Chen et al. "Repurposing Pre-Trained Video Diffusion Models for Event-Based Video Interpolation." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.01162

Markdown

[Chen et al. "Repurposing Pre-Trained Video Diffusion Models for Event-Based Video Interpolation." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/chen2025cvpr-repurposing/) doi:10.1109/CVPR52734.2025.01162

BibTeX

@inproceedings{chen2025cvpr-repurposing,
  title     = {{Repurposing Pre-Trained Video Diffusion Models for Event-Based Video Interpolation}},
  author    = {Chen, Jingxi and Feng, Brandon Y. and Cai, Haoming and Wang, Tianfu and Burner, Levi and Yuan, Dehao and Fermuller, Cornelia and Metzler, Christopher A. and Aloimonos, Yiannis},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {12456-12466},
  doi       = {10.1109/CVPR52734.2025.01162},
  url       = {https://mlanthology.org/cvpr/2025/chen2025cvpr-repurposing/}
}