用流模型建模真实图像噪声，无需依赖元数据即可生成多样噪声。
sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
- 基于归一化流构建新框架，可从图像推断相机设置并分类噪声
- 在基准数据集上生成噪声质量高，去噪性能领先
- 适合图像去噪、真实噪声建模研究者使用
噪声是信号处理中的普遍挑战，尤其在图像去噪领域。尽管卷积神经网络（CNN）已取得显著成果，但其前提假设是噪声服从已知分布，限制了在真实场景中的应用。为克服这一局限，已有研究通过采集真实世界噪声图像数据集来提升模型实用性。生成方法如生成对抗网络（GANs）和归一化流（NFs）被用于生成逼真的噪声图像。然而，现有工作依赖相机元数据进行建模，甚至在采样阶段也需元数据。本文提出一种新方法，无需元数据即可估计底层相机参数，从而改善噪声建模并生成多样化噪声分布。我们引入一个新型归一化流框架，实现基于相机设置的噪声分类与多种噪声图像生成。实验结果表明，该模型生成噪声质量优异，在多个基准数据集上的去噪性能领先。
原文摘要 · Abstract (English)
Noise poses a widespread challenge in signal processing, particularly when it comes to denoising images. Although convolutional neural networks (CNNs) have exhibited remarkable success in this field, they are predicated upon the belief that noise follows established distributions, which restricts their practicality when dealing with real-world noise. To overcome this limitation, several efforts have been taken to collect noisy image datasets from the real world. Generative methods, employing techniques such as generative adversarial networks (GANs) and normalizing flows (NFs), have emerged as a solution for generating realistic noisy images. Recent works model noise using camera metadata, however requiring metadata even for sampling phase. In contrast, in this work, we aim to estimate the underlying camera settings, enabling us to improve noise modeling and generate diverse noise distributions. To this end, we introduce a new NF framework that allows us to both classify noise based on camera settings and generate various noisy images. Through experimental results, our model demonstrates exceptional noise quality and leads in denoising performance on benchmark datasets.
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。