Recently, using diffusion models for zero-shot image restoration (IR) has become a new hot paradigm. This type of method only needs to use the pre-trained off-the-shelf diffusion models, without any finetuning, and can directly handle various IR tasks. The upper limit of the restoration performance depends on the pre-trained diffusion models, which are in rapid evolution. However, current methods only discuss how to deal with fixed-size images, but dealing with images of arbitrary sizes is very important for practical applications. This paper focuses on how to use those diffusion-based zero-shot IR methods to deal with any size while maintaining the excellent characteristics of zero-shot. A simple way to solve arbitrary size is to divide it into fixed-size patches and solve each patch independently. But this may yield significant artifacts since it neither considers the global semantics of all patches nor the local information of adjacent patches. Inspired by the Range-Null space Decomposition, we propose the Mask-Shift Restoration to address local incoherence and propose the Hierarchical Restoration to alleviate out-of-domain issues. Our simple, parameter-free approaches can be used not only for image restoration but also for image generation of unlimited sizes, with the potential to be a general tool for diffusion models. Code: https://github.com/wyhuai/DDNM/tree/main/hq_demo

翻译：近期，利用扩散模型进行零样本图像恢复（IR）已成为新的研究热点。此类方法仅需使用预训练的现成扩散模型，无需任何微调即可直接处理各类图像恢复任务。其恢复性能的上限取决于快速演进的预训练扩散模型。然而现有方法仅探讨如何处理固定尺寸图像，而处理任意尺寸图像对于实际应用至关重要。本文聚焦于如何在保持零样本特性的同时，基于扩散模型的零样本IR方法处理任意尺寸图像。解决任意尺寸的简单方案是将图像分割为固定尺寸的图像块并独立处理每个图像块。但该方法既未考虑所有图像块的全局语义，也未考虑相邻图像块的局部信息，因此可能产生显著伪影。受零空间-值域空间分解启发，我们提出掩码移位恢复方法解决局部不连续性问题，并提出分层恢复方法缓解域外问题。这种无参数、简洁的方法不仅适用于图像恢复，还可用于任意尺寸的图像生成，具有成为扩散模型通用工具的潜力。代码：https://github.com/wyhuai/DDNM/tree/main/hq_demo