计算机工程与应用2025，Vol.61Issue(6)：304-316,13.DOI:10.3778/j.issn.1002-8331.2311-0264
雨痕退化预测与预训练扩散先验的单图像去雨方法
Single Image Deraining Using Rainy Streak Degradation Prediction and Pre-Trained Diffusion Prior
摘要
Abstract
Images captured in rainy weather degrade visual quality and subsequent task accuracy due to interference from rain streaks.To effectively apply the generative prior in the diffusion model as well as to avoid the computational burden of re-training the conditional diffusion model,a single image deraining method combining rain streak degradation predic-tion and unconditional pre-trained diffusion model is proposed,which is achieved by using the convolutional dictionary learning mechanism to obtain rain streak maps with raining images,the rain streak map will be used to bootstrap the null-space diffusion model.Single image deraining using an existing pre-trained unconditional diffusion model,thus effectively improving the quality of image deraining.Compared with other single image deraining methods,the method achieves the highest PSNR improvement of 0.44 dB(+1.1%),SSIM improvement of 0.006(+0.7%),and LPIPS improvement of 0.008(+42.1%)on the Rain100H and Rain100L datasets,achieving the state-of-the-art results so far on both datasets.关键词
单图像去雨/扩散模型/预训练模型Key words
single image deraining/diffusion model/pre-trained model分类
信息技术与安全科学引用本文复制引用
谢瑞麟,吴昊,袁国武..雨痕退化预测与预训练扩散先验的单图像去雨方法[J].计算机工程与应用,2025,61(6):304-316,13.基金项目
国家自然科学基金(62061049,11663007) （62061049,11663007）
兴滇英才支持计划(C6213001221) （C6213001221）
云南省科技厅云南大学双一流建设联合专项(202201BF070001-005). （202201BF070001-005）
