• Important Dates
• Introduction
• Dataset
• Download
• Evaluation

Access the Challenge Dataset

Train Images:   [Baidu Netdisk] [Google Drive]

Train annotation:   [Baidu Netdisk] [Google Drive]

Val Images:   [Baidu Netdisk] [Google Drive]

The Dataset is for this chanllenge and research purpose only. Commercial use is not permitted.

Content of The Downloaded Package

LIS dataset should follow folder structure bellow, it use the same type of annotation with COCO:

├── LIS │ ├── RAW-dark │ │ ├── lis_xxxxxx.png │ ├── annotations │ │ ├──lis_coco_png_raw_dark_trainonly_challenge.json │ │ ├──…

Citation

If you use this dataset for any purpose, please cite our previous work

@article{2023lis, title={Instance Segmentation in the Dark}, author={Chen, Linwei and Fu, Ying and Wei, Kaixuan and Zheng, Dezhi and Heide, Felix}, journal={International Journal of Computer Vision}, volume={131}, number={8}, pages={2198-2218}, year={2023}, publisher={Springer} } @inproceedings{fuying-2021-bmvc, title={Crafting Object Detection in Very Low Light}, author={Yang, Hong and Kaixuan, Wei and Linwei, Chen and Ying, Fu}, booktitle={British Machine Vision Conference (BMVC)}, year={2021} }