Window self-attention based Transformer receives the advanced results in image denoising. However, the current methods still have some limitations in capturing the global dependencies and local responses. To tackle these problems, this paper proposes a novel Transformer based image denoising method, called as CSformer, which is equipped with two key blocks, including the cross-scale features fusion (CS2F) block and mixed global-local Swin (M-Swin) Transformer block. The CSformer has a specific multi-scale framework, in which the multi-scale features, extracted by M-Swin Transformer, are fused using CS2F block. Such cross-scale fusion not only enriches the features, but also yields the multi-scale self-attention. In addition, the M-Swin Transformer block consists of the Swin Transformer block and the separable convolution based convolutional local-extraction (CLE) block, which can boost the ability of Transformer in local representation. We demonstrate the superiority of CSformer on some well-known datasets at different noise levels with comparisons to several state-of-the-art methods.

中文翻译：

---

CSformer：用于图像去噪的基于跨尺度特征融合的变压器


基于窗口自注意力的 Transformer 在图像去噪方面取得了先进的成果。然而，当前的方法在捕获全局依赖性和局部响应方面仍然存在一些局限性。为了解决这些问题，本文提出了一种新颖的基于 Transformer 的图像去噪方法，称为 CSformer，该方法配备两个关键模块，包括跨尺度特征融合（CS2F）模块和混合全局局部 Swin（M-Swin）变压器块。 CSformer 具有特定的多尺度框架，其中 M-Swin Transformer 提取的多尺度特征使用 CS2F 块进行融合。这种跨尺度融合不仅丰富了特征，而且产生了多尺度自注意力。此外，M-Swin Transformer 模块由 Swin Transformer 模块和基于可分离卷积的卷积局部提取（CLE）模块组成，可以增强 Transformer 的局部表示能力。我们通过与几种最先进的方法进行比较，证明了 CSformer 在不同噪声水平下的一些著名数据集上的优越性。