跨范式表征与对齐变换器用于图像去雨
Cross Paradigm Representation and Alignment Transformer for Image Deraining
AI总结：
本文提出CPRAformer，通过整合全局-局部和空间-通道表征，解决单范式架构在不规则雨点和复杂几何重叠下的挑战，提升图像去雨性能。
摘要：
基于Transformer的网络通过利用空间或通道级自注意力，在低级视觉任务如图像去雨中取得了优异性能。然而，不规则雨点模式和复杂几何重叠挑战了单范式架构，需要统一框架整合互补的全局-局部和空间-通道表征。为此，我们提出了一种新颖的跨范式表征与对齐变换器（CPRAformer）。其核心思想是层次化表征与对齐，利用两种范式（空间-通道和全局-局部）的优势来辅助图像重建。它在范式内和范式间架起桥梁，对齐并协调它们以实现深度特征交互和融合。具体而言，我们使用两种类型的自注意力：稀疏提示通道自注意力（SPC-SA）和空间像素细化自注意力（SPR-SA）。SPC-SA通过动态稀疏性增强全局通道依赖性，而SPR-SA专注于空间雨分布和细粒度纹理恢复。为了解决它们之间的特征错位和知识差异，我们引入了自适应对齐频率模块（AAFM），通过两阶段渐进方式对齐和交互特征，实现自适应指导和互补性。这减少了范式内和范式间的信息差距。通过这种统一的跨范式动态交互框架，我们实现了从两种范式中提取最有价值的交互融合信息。大量实验表明，我们的模型在八个基准数据集上取得了最先进的性能，并进一步验证了CPRAformer在其他图像修复任务和下游应用中的鲁棒性。
英文摘要：
Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge single-paradigm architectures, necessitating a unified framework to integrate complementary global-local and spatial-channel representations. To address this, we propose a novel Cross Paradigm Representation and Alignment Transformer (CPRAformer). Its core idea is the hierarchical representation and alignment, leveraging the strengths of both paradigms (spatial-channel and global-local) to aid image reconstruction. It bridges the gap within and between paradigms, aligning and coordinating them to enable deep interaction and fusion of features. Specifically, we use two types of self-attention in the Transformer blocks: sparse prompt channel self-attention (SPC-SA) and spatial pixel refinement self-attention (SPR-SA). SPC-SA enhances global channel dependencies through dynamic sparsity, while SPR-SA focuses on spatial rain distribution and fine-grained texture recovery. To address the feature misalignment and knowledge differences between them, we introduce the Adaptive Alignment Frequency Module (AAFM), which aligns and interacts with features in a two-stage progressive manner, enabling adaptive guidance and complementarity. This reduces the information gap within and between paradigms. Through this unified cross-paradigm dynamic interaction framework, we achieve the extraction of the most valuable interactive fusion information from the two paradigms. Extensive experiments demonstrate that our model achieves state-of-the-art performance on eight benchmark datasets and further validates CPRAformer's robustness in other image restoration tasks and downstream applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
