Cloud-Surface Recovery Difficulty-graded Dataset
收藏IEEE2026-04-17 收录
下载链接：
https://ieee-dataport.org/documents/latent-feature-disentanglement-bidirectional-prompting-network-unsupervised-cloud-removal
下载链接
链接失效反馈官方服务：
资源简介：
The Cloud-Surface Recovery Difficulty-graded Dataset is designed for evaluating cloud removal techniques by categorizing cloudy images into three difficulty levels: Easy, Medium, and Hard. These difficulty levels are based on the complexity of the cloud cover and its interaction with the underlying surface. Additionally, the dataset is further divided into four seasonal subsets\u2014Spring, Summer, Autumn, and Winter\u2014resulting in a total of 12 subsets. Each subset represents cloud images from a specific season and difficulty level, providing a diverse set of images that allow for thorough testing and benchmarking of cloud removal models across different cloud coverages and seasonal conditions.
提供机构：
Zhixuan Huang
