This is the repository for the LLE-VOS Dataset.
The LLE-VOS dataset includes 70 videos, consisting of paired normal and low-light videos, along with their corresponding segmentation annotations and event streams. The videos are recorded at a diverse range of locations, including gyms, playgrounds, classrooms, meeting rooms, and zoos.
The current version of the dataset contains:
To download the dataset, please click this link.
If you use this data, please cite the following papers:
Li, Hebei, Jin Wang, Jiahui Yuan, Yue Li, Wenming Weng, Yansong Peng, Yueyi Zhang, Zhiwei Xiong, and Xiaoyan Sun. "Event-assisted Low-Light Video Object Segmentation." CVPR 2024.
@article{li2024event,
title={Event-assisted Low-Light Video Object Segmentation},
author={Li, Hebei and Wang, Jin and Yuan, Jiahui and Li, Yue and Weng, Wenming and Peng, Yansong and Zhang, Yueyi and Xiong, Zhiwei and Sun, Xiaoyan},
booktitle={CVPR},
year={2024}
}