Neural Schrödinger bridge for unpaired real-world image deraining

Given the significant differences between domains, current unpaired learning methods struggle to accurately map the relationship between rainy and clear images. To this end, we introduce a neural Schr & ouml;dinger bridge (NSB) for unpaired real-world image deraining, which utilizes the stochastic differential equations to capture the mapping relationships between rainy and clear domains. Meanwhile, we frame the deraining process as a Lagrangian problem using the KullbackLeibler divergence between the data distribution and the model distribution. Additionally, by leveraging the capabilities of the contrastive language-image pre-training model (CLIP), our research shows that the CLIP prior helps differentiate between rainy and clear images. Building on this, we reformulate the Schr & ouml;dinger bridge problem as a series of adversarial learning tasks using both image and prompt representations. To our knowledge, our approach is the first to use the Schr & ouml;dinger bridge in unpaired image deraining. Extensive experiments show that our proposed NSB model outperforms existing unpaired deraining methods in both quantitative and qualitative evaluations.