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 prediction 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.

Key words: single image deraining, diffusion model, pre-trained model

摘要： 雨天拍摄的图像由于雨痕干扰，会降低视觉质量和后续任务精度。为有效应用扩散模型中的生成式先验以及避免重新训练条件扩散模型带来的计算负担，提出了一种结合雨痕退化预测与无条件预训练扩散模型的单图像去雨方法，通过使用卷积字典学习机制在雨痕退化预测网络中获取带雨图像的雨痕图，将雨痕图用于引导零空间扩散模型，实现了使用在已有的预训练无条件扩散模型下进行单图像去雨，从而有效地提高了图像去雨的质量。和其他单图像去雨方法相比，该方法在Rain100H和Rain100L数据集上取得了目前最好的结果，PSNR指标最大提升了0.44?dB（+1.1%），SSIM指标最大提升了0.006（+0.7%），LPIPS指标最大提升了0.008（+42.1%）。

关键词: 单图像去雨, 扩散模型, 预训练模型