论文标题
富集的CNN转换器特征聚合网络，用于超分辨率
Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution
论文作者
论文摘要
最新的基于变压器的超分辨率（SR）方法已针对基于CNN的常规方法取得了有希望的结果。但是，这些方法仅利用基于自我注意的推理而产生的基本短视。在本文中，我们引入了一个有效的混合SR网络，以汇总丰富的功能，包括来自CNN的本地功能和Transformers捕获的远程多尺度依赖性。具体而言，我们的网络包括变压器和卷积分支，它们在恢复过程中协同补充了每个表示形式。此外，我们提出了一个跨尺度令牌注意模块，使变压器分支可以有效地利用令牌之间的信息关系。我们提出的方法在许多基准数据集上实现了最先进的SR。
Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods. However, these approaches suffer from essential shortsightedness created by only utilizing the standard self-attention-based reasoning. In this paper, we introduce an effective hybrid SR network to aggregate enriched features, including local features from CNNs and long-range multi-scale dependencies captured by transformers. Specifically, our network comprises transformer and convolutional branches, which synergetically complement each representation during the restoration procedure. Furthermore, we propose a cross-scale token attention module, allowing the transformer branch to exploit the informative relationships among tokens across different scales efficiently. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
