提出新方法让自监督图像修复适配非高斯噪声，提升低光等场景效果。
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
- 将原有方法扩展至处理泊松、伽马等非高斯噪声，适用性更广。
- 理论证明新损失函数无偏，能准确逼近有监督损失。
- 在低光成像和雷达等领域表现优于现有自监督方法。
Recorrupted-to-Recorrupted（R2R）是一种仅用噪声测量数据进行自监督训练深度网络的图像修复方法，在高斯噪声下其期望与监督平方损失等价。然而，其在非高斯噪声下的有效性尚未探索。本文提出广义R2R（GR2R），将R2R框架拓展至处理对数瑞利噪声，并适用于自然指数族噪声（如泊松和伽马分布），这类噪声在低光成像和合成孔径雷达中具有关键作用。我们证明了GR2R损失是监督损失的无偏估计，且常用的Stein无偏风险估计器可视为其特例。一系列实验在高斯、泊松和伽马噪声下验证了GR2R的有效性，结果表明其性能优于其他自监督方法。
原文摘要 · Abstract (English)
Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demonstrating equivalence in expectation to the supervised squared loss in the case of Gaussian noise. However, its effectiveness with non-Gaussian noise remains unexplored. In this paper, we propose Generalized R2R (GR2R), extending the R2R framework to handle a broader class of noise distribution as additive noise like log-Rayleigh and address the natural exponential family including Poisson and Gamma noise distributions, which play a key role in many applications including low-photon imaging and synthetic aperture radar. We show that the GR2R loss is an unbiased estimator of the supervised loss and that the popular Stein's unbiased risk estimator can be seen as a special case. A series of experiments with Gaussian, Poisson, and Gamma noise validate GR2R's performance, showing its effectiveness compared to other self-supervised methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。