The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors. Two efficient and generic techniques: pattern-aligned patch sampling and high-bit reconstruction help accurate synthesis of spatial-correlated noise and high-bit noise respectively. We conduct systematic experiments on SIDD and ELD datasets. The results show that (1) our method outperforms existing methods and demonstrates wide generalization on different sensors and lighting conditions. (2) Recent conclusions derived from DNN-based noise modeling methods are actually based on inaccurate noise parameters. The DNN-based methods still cannot outperform physics-based statistical methods.

翻译：大规模真实原始图像去噪数据集的缺乏给合成用于训练去噪模型的真实原始图像噪声带来了挑战。然而，真实原始图像噪声由多种噪声源共同贡献，且在不同传感器之间差异显著。现有方法无法精确建模所有噪声源，且为每个传感器构建噪声模型也十分繁琐。本文提出一种新视角：通过直接从传感器的真实噪声中采样来合成噪声。该方法能够为不同相机传感器本质性地生成准确的原始图像噪声。两种高效且通用的技术——模式对齐的补丁采样和高位重建——分别有助于精确合成空间相关噪声和高位噪声。我们在SIDD和ELD数据集上进行了系统实验。结果表明：（1）我们的方法优于现有方法，并在不同传感器和光照条件下展现出广泛的泛化能力；（2）近期基于深度神经网络（DNN）的噪声建模方法所得出的结论实际上基于不准确的噪声参数，基于DNN的方法仍无法超越基于物理的统计方法。