Image denoising is a fundamental problem in computer vision and medical imaging. However, real-world images are often degraded by structured noise with strong anisotropic correlations that existing methods struggle to remove. Most data-driven approaches rely on large datasets with high-quality labels and still suffer from limited generalizability, whereas existing zero-shot methods avoid this limitation but remain effective only for independent and identically distributed (i.i.d.) noise. To address this gap, we propose Median2Median (M2M), a zero-shot denoising framework designed for structured noise. M2M introduces a novel sampling strategy that generates pseudo-independent sub-image pairs from a single noisy input. This strategy leverages directional interpolation and generalized median filtering to adaptively exclude values distorted by structured artifacts. To further enlarge the effective sampling space and eliminate systematic bias, a randomized assignment strategy is employed, ensuring that the sampled sub-image pairs are suitable for Noise2Noise training. In our realistic simulation studies, M2M performs on par with state-of-the-art zero-shot methods under i.i.d. noise, while consistently outperforming them under correlated noise. These findings establish M2M as an efficient, data-free solution for structured noise suppression and mark the first step toward effective zero-shot denoising beyond the strict i.i.d. assumption.

翻译：图像去噪是计算机视觉和医学成像领域的一个基本问题。然而，现实世界中的图像常常受到具有强各向异性相关性的结构化噪声的退化，现有方法难以有效去除此类噪声。大多数数据驱动方法依赖于带有高质量标签的大型数据集，但仍受限于泛化能力不足；而现有的零样本方法虽然避免了这一限制，却仅对独立同分布噪声保持有效。为填补这一空白，我们提出了Median2Median（M2M），一个专为结构化噪声设计的零样本去噪框架。M2M引入了一种新颖的采样策略，能够从单张噪声输入图像中生成伪独立的子图像对。该策略利用方向性插值和广义中值滤波，自适应地排除受结构化伪影扭曲的像素值。为进一步扩大有效采样空间并消除系统偏差，我们采用了随机分配策略，确保采样的子图像对适用于Noise2Noise训练。在真实的模拟研究中，M2M在独立同分布噪声条件下的表现与最先进的零样本方法相当，而在相关噪声条件下则始终优于这些方法。这些发现确立了M2M作为一种高效、无需数据的结构化噪声抑制解决方案，并标志着在超越严格独立同分布假设、实现有效零样本去噪的道路上迈出了第一步。