Although deep learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing methods address this issue by improving data synthesis pipelines, estimating degradation kernels, employing deep internal learning, and performing domain adaptation and regularization. Previous domain adaptation methods have sought to bridge the domain gap by learning domain-invariant knowledge in either feature or pixel space. However, these techniques often struggle to extend to low-level vision tasks within a stable and compact framework. In this paper, we show that it is possible to perform domain adaptation via the noise-space using diffusion models. In particular, by leveraging the unique property of how the multi-step denoising process is influenced by auxiliary conditional inputs, we obtain meaningful gradients from noise prediction to gradually align the restored results of both synthetic and real-world data to a common clean distribution. We refer to this method as denoising as adaptation. To prevent shortcuts during training, we present useful techniques such as channel shuffling and residual-swapping contrastive learning. Experimental results on three classical image restoration tasks, namely denoising, deblurring, and deraining, demonstrate the effectiveness of the proposed method. Code will be released at: https://github.com/KangLiao929/Noise-DA/.

翻译：尽管基于深度学习的图像复原方法已取得显著进展，但由于在合成数据上训练导致的显著领域差异，这些方法在泛化到真实场景时仍面临局限。现有方法通过改进数据合成流程、估计退化核、采用深度内部学习以及执行领域自适应与正则化来应对此问题。以往的领域自适应方法试图通过在特征空间或像素空间学习领域不变知识来弥合领域差距。然而，这些技术往往难以在稳定紧凑的框架内扩展至低层视觉任务。本文证明，利用扩散模型可在噪声空间实现领域自适应。具体而言，通过利用多步去噪过程受辅助条件输入影响的独特性质，我们从噪声预测中获得有意义的梯度，逐步将合成数据与真实数据的复原结果对齐至共同的清晰分布。我们将此方法称为"去噪即适配"。为防止训练过程中的捷径行为，我们提出了通道混洗与残差交换对比学习等有效技术。在去噪、去模糊和去雨三个经典图像复原任务上的实验结果验证了所提方法的有效性。代码发布于：https://github.com/KangLiao929/Noise-DA/。