π Accepted at ICCV 2025
π¨βπ» Authors:Β Β
- Taewoo Kim (KAIST)Β Β
- Kuk-Jin Yoon (KAIST)
π Links:Β Β
- π [Paper (PDF)] /Β π [Dataset] / π» [Code]
π Abstract:Β Β
In low-light environments, longer exposure times are commonly used to enhance image visibility; however, this inevitably leads to motion blur. Even with a long exposure time, videos captured in low-light environments still suffer from issues such as low visibility, low contrast, and color distortion. Additionally, the long exposure time results in videos with a low frame rate. Therefore, videos captured in low-light exhibit low visibility and motion blur, as well as low frame rates. To overcome these limitations, we propose a novel problem aimed at transforming motion-blurred, low-frame-rate videos with poor visibility in low-light environments into high-frame-rate videos while simultaneously enhancing their visibility. To tackle this challenge, we leverage the unique advantages of event cameras, which capture scene changes asynchronously, providing superior temporal resolution and a wider dynamic range compared to conventional frame-based cameras. These properties make event cameras particularly effective in reducing motion blur, compensating for low frame rates, and enhancing visibility in low-light conditions. To this end, we developed a hybrid camera system that integrates two RGB cameras and an event camera, capturing a dedicated dataset for this task and proposing novel network architectures to effectively address this problem.
π Citation (BibTeX):
@inproceedings{kim2025event,
title={Event-guided Unified Framework for Low-light Video Enhancement, Frame Interpolation, and Deblurring},
author={Kim, Taewoo and Yoon, Kuk-Jin},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
year={2025}
}