基于归一化流的噪声感知采样实现sRGB真实噪声建模
sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
- Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出一种新的归一化流框架，通过估计相机设置实现sRGB真实噪声建模，可分类噪声并生成多样含噪图像，在基准数据集上的去噪性能优异。
AI中文摘要：
噪声是信号处理中普遍存在的挑战，尤其在图像去噪领域。尽管卷积神经网络（CNN）在该领域表现出色，但它们基于噪声遵循既定分布的假设，这限制了其处理真实世界噪声的实用性。为克服这一局限，已有多项工作致力于收集真实世界的含噪图像数据集，生成式方法（如生成对抗网络（GAN）和归一化流（NF））成为生成逼真含噪图像的解决方案。近期研究利用相机元数据对噪声建模，但采样阶段仍需元数据。相比之下，本研究旨在估计潜在的相机设置，以改进噪声建模并生成多样的噪声分布。为此，我们引入一种新的NF框架，该框架既能基于相机设置对噪声分类，又能生成各类含噪图像。实验结果表明，我们的模型展现出优异的噪声质量，且在基准数据集上的去噪性能领先。
英文摘要：
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.
