Xformer：用于图像去噪的混合X形Transformer
Xformer: Hybrid X-Shaped Transformer for Image Denoising
AI总结：
本文提出混合X形Transformer架构Xformer，通过空间与通道双分支Transformer块及双向连接单元实现多尺度全局信息建模，在合成与真实图像去噪任务上以相当复杂度取得最先进性能。
摘要：
在本文中，我们提出了一种混合X形视觉Transformer，名为Xformer，它在图像去噪任务上表现突出。我们探索了从不同范围增强token的全局表示。具体而言，我们采用了两种类型的Transformer块。空间维度Transformer块在由空间维度定义的token之间执行细粒度局部patch交互。通道维度Transformer块在由通道维度定义的token之间执行直接的全局上下文交互。基于并行的网络结构，我们设计了两个分支来执行这两种交互方式。在每个分支内，我们采用编码器-解码器架构来捕获多尺度特征。此外，我们提出了双向连接单元（BCU）来耦合这两个分支学习到的表示，同时提供增强的信息融合。这些联合设计使我们的Xformer能够在空间和通道维度上进行强大的全局信息建模。大量实验表明，在相当的模型复杂度下，Xformer在合成和真实世界图像去噪任务上达到了最先进的性能。我们还在https://github.com/gladzhang/Xformer提供了代码和模型。
英文摘要：
In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two types of Transformer blocks. The spatial-wise Transformer block performs fine-grained local patches interactions across tokens defined by spatial dimension. The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension. Based on the concurrent network structure, we design two branches to conduct these two interaction fashions. Within each branch, we employ an encoder-decoder architecture to capture multi-scale features. Besides, we propose the Bidirectional Connection Unit (BCU) to couple the learned representations from these two branches while providing enhanced information fusion. The joint designs make our Xformer powerful to conduct global information modeling in both spatial and channel dimensions. Extensive experiments show that Xformer, under the comparable model complexity, achieves state-of-the-art performance on the synthetic and real-world image denoising tasks. We also provide code and models at https://github.com/gladzhang/Xformer.
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。
