2026-10-13T02:25:21Z https://www.scidb.cn/oai

10.57760/sciencedb.j00232.0000z 2026-09-16T17:40:32Z

2026-09-16 WHU-HRTCC: A Benchmark Dataset for Thin Cloud Correction in High-Resolution GF-Series Remote Sensing Imagery doi:10.57760/sciencedb.j00232.0000z en WHU-HRTCC contains 10,000 paired cloudy and cloud-free RGB remote sensing image patches for high-resolution thin cloud correction. Each sample has a spatial size of 512 × 512 pixels. The dataset is divided into training, validation, and test subsets at a ratio of 7:2:1. Each cloudy image has a spatially corresponding cloud-free reference image. The samples cover five dominant land-cover categories: vegetation, cropland, built-up areas, water bodies, and bare land. Please refer to the associated paper for detailed information on data generation, thin-cloud simulation, scene sampling, and benchmark experiments. high-resolution remote sensing; thin cloud correction; benchmark dataset; cloud synthesis; deep learning Xu Liying Yang Zhiyuan Li Huifang Shen Huanfeng PUBLIC https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset Science Data Bank