Supervised Gaussian denoisers exhibit limited generalization when confronted with out-of-distribution noise, due to the diverse distributional characteristics of different noise types. To bridge this gap, we propose a histogram matching approach that transforms arbitrary noise towards a target Gaussian distribution with known intensity. Moreover, a mutually reinforcing cycle is established between noise transformation and subsequent denoising. This cycle progressively refines the noise to be converted, making it approximate the real noise, thereby enhancing the noise transformation effect and further improving the denoising performance. We tackle specific noise complexities: local histogram matching handles signal-dependent noise, intrapatch permutation processes channel-related noise, and frequency-domain histogram matching coupled with pixel-shuffle down-sampling breaks spatial correlation. By applying these transformations, a single Gaussian denoiser gains remarkable capability to handle various out-of-distribution noises, including synthetic noises such as Poisson, salt-and-pepper and repeating pattern noises, as well as complex real-world noises. Extensive experiments demonstrate the superior generalization and effectiveness of our method.

翻译：监督式高斯去噪器在面对分布外噪声时表现出有限的泛化能力，这源于不同噪声类型多样化的分布特性。为弥合这一差距，我们提出一种直方图匹配方法，可将任意噪声向具有已知强度的目标高斯分布转换。此外，我们在噪声转换与后续去噪之间建立了相互强化的循环机制。该循环逐步优化待转换噪声，使其逼近真实噪声，从而提升噪声转换效果并进一步提高去噪性能。我们针对特定噪声复杂性提出了解决方案：局部直方图匹配处理信号相关噪声，块内置换处理通道相关噪声，频域直方图匹配结合像素混洗下采样则用于打破空间相关性。通过应用这些转换，单一高斯去噪器获得了显著处理各种分布外噪声的能力，包括泊松噪声、椒盐噪声和重复模式噪声等合成噪声，以及复杂的真实世界噪声。大量实验证明了我们方法卓越的泛化能力和有效性。