Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of information. Besides, existing methods always use a multi-supervised method to aggregate different feature maps, which can not effectively aggregate hierarchical feature information. To address these issues, we propose an attention cube network (A-CubeNet) for image restoration for more powerful feature expression and feature correlation learning. Specifically, we design a novel attention mechanism from three dimensions, namely spatial dimension, channel-wise dimension and hierarchical dimension. The adaptive spatial attention branch (ASAB) and the adaptive channel attention branch (ACAB) constitute the adaptive dual attention module (ADAM), which can capture the long-range spatial and channel-wise contextual information to expand the receptive field and distinguish different types of information for more effective feature representations. Furthermore, the adaptive hierarchical attention module (AHAM) can capture the long-range hierarchical contextual information to flexibly aggregate different feature maps by weights depending on the global context. The ADAM and AHAM cooperate to form an "attention in attention" structure, which means AHAM's inputs are enhanced by ASAB and ACAB. Experiments demonstrate the superiority of our method over state-of-the-art image restoration methods in both quantitative comparison and visual analysis.

中文翻译：

---

用于图像恢复的注意立方体网络

近年来，深度卷积神经网络（CNN）在图像恢复中得到了广泛的应用，并取得了巨大的成功。然而，大多数现有方法仅限于局部感受野和对不同类型信息的平等对待。此外，现有的方法总是使用多监督的方法来聚合不同的特征图，不能有效地聚合层次特征信息。为了解决这些问题，我们提出了一种用于图像恢复的注意力立方体网络（A-CubeNet），以实现更强大的特征表达和特征相关学习。具体来说，我们从三个维度设计了一种新颖的注意力机制，即空间维度、通道维度和层次维度。自适应空间注意力分支（ASAB）和自适应通道注意力分支（ACAB）构成了自适应双重注意力模块（ADAM），可以捕获长距离的空间和通道上下文信息来扩展感受野并区分不同类型信息以获得更有效的特征表示。此外，自适应分层注意模块（AHAM）可以捕获远程分层上下文信息，根据全局上下文通过权重灵活地聚合不同的特征图。ADAM 和 AHAM 合作形成“attention in attention”结构，这意味着 AHAM 的输入由 ASAB 和 ACAB 增强。