2026-10-15T03:09:26Z https://www.scidb.cn/oai

10.57760/sciencedb.j00240.00269 2026-07-20T17:38:57Z

2026-07-20 Dataset for "Spatial-Frequency Multi-Scale Sparse Attention for Single Image Raindrop Removal" doi:10.57760/sciencedb.j00240.00269 en This dataset is the associated data for the paper “Spatial-Frequency Multi-Scale Sparse Attention for Single Image Raindrop Removal” (SFFormer), comprising the complete image data and experimental configuration files required for model training, validation, and testing. The dataset covers three public benchmark datasets: the AGAN-Data raindrop removal dataset (861 training image pairs, 58 testing image pairs), the SPAD rain streak removal dataset (14,000 training image pairs, 1,000 testing image pairs), and the Dense-Haze real-world haze removal dataset. All images are cropped to 256×256 patches and organized into training and test sets following the original splits. Additionally, the package includes the complete training and testing code for the SFFormer model, pre-trained weight files, and ablation study configuration files, which can be used to reproduce all experimental results presented in the paper. This dataset is openly shared under the CC BY-NC-ND 4.0 license. Researchers in related fields are welcome to use it and cite the paper. single image deraining; image restoration; spatial-frequency joint processing; uncertainty guidance; sparse attention; Transformer; AGAN-Data; SPAD; Dense-Haze; associated data Lin Xiao Dong Dateng Li Yan Yang Qizhe EMBARGO https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset Science Data Bank