Recently, many self-supervised learning methods for image reconstruction have been proposed that can learn from noisy data alone, bypassing the need for ground-truth references. Most existing methods cluster around two classes: i) Noise2Self and similar cross-validation methods that require very mild knowledge about the noise distribution, and ii) Stein's Unbiased Risk Estimator (SURE) and similar approaches that assume full knowledge of the distribution. The first class of methods is often suboptimal compared to supervised learning, and the second class tends to be impractical, as the noise level is often unknown in real-world applications. In this paper, we provide a theoretical framework that characterizes this expressivity-robustness trade-off and propose a new approach based on SURE, but unlike the standard SURE, does not require knowledge about the noise level. Throughout a series of experiments, we show that the proposed estimator outperforms other existing self-supervised methods on various imaging inverse problems

翻译：近年来，许多用于图像重建的自监督学习方法被提出，这些方法仅需从含噪数据中学习，无需真实参考数据。现有方法主要围绕两类展开：i) Noise2Self及类似交叉验证方法，仅需关于噪声分布的极微弱先验知识；ii) 斯坦无偏风险估计器（SURE）及类似方法，要求完全已知噪声分布。第一类方法相较于监督学习常存在次优性，而第二类方法在实际应用中往往不具可行性，因为真实场景中的噪声水平通常未知。本文提出一个理论框架以刻画这种表达能力与鲁棒性之间的权衡，并基于SURE提出一种新方法——与标准SURE不同，该方法无需已知噪声水平。通过一系列实验，我们证明所提出的估计器在多种成像逆问题上均优于现有自监督方法。