提出路由窗口注意力机制，高效建模中距离图像上下文。
RouteWinFormer: A Route-Window Transformer for Middle-range Attention in Image Restoration
- 动态选择相似区域窗口进行注意力聚合，提升中距离建模效率。
- 在9个数据集上优于现有方法，结构与退化特征分离学习。
- 适合需要高效建模局部到中距离依赖的图像修复任务。
Transformer 模型因能捕捉长程像素依赖而在图像修复领域备受关注。然而，长程注意力常带来不必要的计算开销，因退化和上下文通常具有局部性。各类退化数据集的归一化平均注意力距离显示，中距离注意力已足够。基于此，我们提出 RouteWinFormer，一种新型基于窗口的 Transformer，用于图像修复中的中距离上下文建模。该模型引入路由窗口注意力模块（Route-Windows Attention Module），根据区域相似性动态选择相关邻近窗口进行注意力聚合，高效扩展感受野至中等范围。此外，训练中引入多尺度结构正则化，使 U 型网络的子尺度专注结构信息，原尺度则基于通用图像结构先验学习退化模式。大量实验表明，RouteWinFormer 在 9 个数据集上的多种图像修复任务中均超越现有最先进方法。
原文摘要 · Abstract (English)
Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical necessity, as degradation and context are typically localized. Normalized average attention distance across various degradation datasets shows that middle-range attention is enough for image restoration. Building on this insight, we propose RouteWinFormer, a novel window-based Transformer that models middle-range context for image restoration. RouteWinFormer incorporates Route-Windows Attnetion Module, which dynamically selects relevant nearby windows based on regional similarity for attention aggregation, extending the receptive field to a mid-range size efficiently. In addition, we introduce Multi-Scale Structure Regularization during training, enabling the sub-scale of the U-shaped network to focus on structural information, while the original-scale learns degradation patterns based on generalized image structure priors. Extensive experiments demonstrate that RouteWinFormer outperforms state-of-the-art methods across 9 datasets in various image restoration tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。