Modeling and synthesizing low-light raw noise is a fundamental problem for computational photography and image processing applications. Although most recent works have adopted physics-based models to synthesize noise, the signal-independent noise in low-light conditions is far more complicated and varies dramatically across camera sensors, which is beyond the description of these models. To address this issue, we introduce a new perspective to synthesize the signal-independent noise by a generative model. Specifically, we synthesize the signal-dependent and signal-independent noise in a physics- and learning-based manner, respectively. In this way, our method can be considered as a general model, that is, it can simultaneously learn different noise characteristics for different ISO levels and generalize to various sensors. Subsequently, we present an effective multi-scale discriminator termed Fourier transformer discriminator (FTD) to distinguish the noise distribution accurately. Additionally, we collect a new low-light raw denoising (LRD) dataset for training and benchmarking. Qualitative validation shows that the noise generated by our proposed noise model can be highly similar to the real noise in terms of distribution. Furthermore, extensive denoising experiments demonstrate that our method performs favorably against state-of-the-art methods on different sensors.

翻译：建模与合成低光照原始噪声是计算摄影与图像处理应用中的基础问题。尽管近年来多数研究采用基于物理的模型进行噪声合成，但低光照条件下的信号无关噪声更为复杂，且在不同相机传感器间差异显著，远超现有模型描述能力。为应对这一挑战，我们提出一种新视角：通过生成模型合成信号无关噪声。具体而言，我们分别以基于物理与基于学习的方式合成信号相关噪声与信号无关噪声。通过此方式，本方法可视为通用模型，能够同时学习不同ISO等级下的噪声特征，并泛化至多种传感器。随后，我们提出一种高效的多尺度判别器——傅里叶变换判别器（FTD），以精准区分噪声分布。此外，我们构建了新的低光照原始去噪数据集（LRD）用于训练与基准测试。定性验证表明，本模型生成的噪声在分布上与真实噪声高度相似。而广泛的去噪实验证实，本方法在不同传感器上的表现均优于当前最先进技术。