The aim of this paper is to propose a mechanism to efficiently and explicitly model image hierarchies in the global, regional, and local range for image restoration. To achieve that, we start by analyzing two important properties of natural images including cross-scale similarity and anisotropic image features. Inspired by that, we propose the anchored stripe self-attention which achieves a good balance between the space and time complexity of self-attention and the modelling capacity beyond the regional range. Then we propose a new network architecture dubbed GRL to explicitly model image hierarchies in the Global, Regional, and Local range via anchored stripe self-attention, window self-attention, and channel attention enhanced convolution. Finally, the proposed network is applied to 7 image restoration types, covering both real and synthetic settings. The proposed method sets the new state-of-the-art for several of those. Code will be available at https://github.com/ofsoundof/GRL-Image-Restoration.git.

翻译：本文旨在提出一种机制，用于在全局、区域和局部范围内高效且显式地建模图像层次结构以进行图像复原。为此，我们首先分析自然图像的两个重要特性（包括跨尺度相似性和各向异性图像特征），并据此提出锚定条带状自注意力机制，该机制在自注意力的空间与时间复杂度以及超出区域范围的建模能力之间实现了良好平衡。然后，我们提出一种名为GRL的新型网络架构，通过锚定条带状自注意力、窗口自注意力和通道注意力增强卷积，在全局、区域和局部范围内显式建模图像层次结构。最后，将所提出的网络应用于涵盖真实和合成场景的7种图像复原任务。所提方法在多项任务中刷新了当前最优性能。代码将开源于https://github.com/ofsoundof/GRL-Image-Restoration.git。