Skip to content

chi-kaichen/S2-ShadowNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 

Repository files navigation

Weakly Supervised Shadow Removal Benchmark (WSSR)

Download WSSR from Baidu Cloud: https://pan.baidu.com/s/1VSIDz9n0LVWJum6ulP5wSw?pwd=1004 key: 1004

WSSR provides 1000 shadow images with 4K resolution and corresponding shadow masks. In addition, we captured non-consistent shadow-free images, which can be used for the implementation of unsupervised shadow removal methods.

Notably, we cropped 1000 shadow images into 4000 patches for training and testing. In the link, we provide 4K resolution version, which makes it easy for users to adjust the sample size and number by themselves.

Contact Us

If you have any questions, please contact us (chikaichen@mail.nwpu.edu.cn).

Acknowledgments

Code is implemented based on https://github.com/XJTU-XGU/RSDA and https://github.com/hhqweasd/G2R-ShadowNet.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published