NM-FlowGAN：使用归一化流与GAN的混合方法在无配对图像条件下建模sRGB噪声
NM-FlowGAN: Modeling sRGB Noise without Paired Images using a Hybrid Approach of Normalizing Flows and GAN
AI总结：
针对真实sRGB噪声建模难、现有生成方法有性能局限且需配对图像的问题，提出结合归一化流与GAN的NM-FlowGAN混合模型，无需配对图像即可合成噪声，在噪声合成及下游去噪任务上均优于基线。
摘要：
建模与合成真实sRGB噪声对各类低层视觉任务至关重要，例如构建用于训练图像去噪系统的数据集。真实sRGB噪声的分布极为复杂，受多种因素影响，因此对其进行精准建模极具挑战性。为此，近期研究提出了采用数据驱动生成模型的方法，例如生成对抗网络（Generative Adversarial Networks, GAN）和归一化流（Normalizing Flows）。这类研究相比传统噪声建模方法，实现了更精准的sRGB噪声建模。但由于各类生成模型的固有特性，现有方法仍存在性能局限。\n为解决这一问题，我们提出NM-FlowGAN——一种结合GAN与归一化流二者优势的混合方法。我们将基于归一化流的逐像素噪声建模网络与基于GAN的空间相关性建模网络相结合。具体而言，逐像素噪声建模网络利用归一化流的高训练稳定性，捕捉受多种因素影响的噪声特征；空间相关性网络则高效建模像素间的关联。值得注意的是，与依赖配对噪声图像的近期方法不同，我们的方法使用干净图像以及影响噪声特征的因素（例如相机型号、ISO设置这类易获取的参数）来合成噪声，因此可应用于无法获取噪声-干净图像对的各类领域。\n在实验中，我们的NM-FlowGAN在sRGB噪声合成任务上的表现优于其他基线方法。此外，使用我们的模型生成的合成图像对训练的去噪神经网络，相比其他基线也展现出更优的性能。我们的代码可在以下地址获取：https://github.com/YoungJooHan/NM-FlowGAN。
英文摘要：
Modeling and synthesizing real sRGB noise is crucial for various low-level vision tasks, such as building datasets for training image denoising systems. The distribution of real sRGB noise is highly complex and affected by a multitude of factors, making its accurate modeling extremely challenging. Therefore, recent studies have proposed methods that employ data-driven generative models, such as Generative Adversarial Networks (GAN) and Normalizing Flows. These studies achieve more accurate modeling of sRGB noise compared to traditional noise modeling methods. However, there are performance limitations due to the inherent characteristics of each generative model. To address this issue, we propose NM-FlowGAN, a hybrid approach that exploits the strengths of both GAN and Normalizing Flows. We combine pixel-wise noise modeling networks based on Normalizing Flows and spatial correlation modeling networks based on GAN. Specifically, the pixel-wise noise modeling network leverages the high training stability of Normalizing Flows to capture noise characteristics that are affected by a multitude of factors, and the spatial correlation networks efficiently model pixel-to-pixel relationships. In particular, unlike recent methods that rely on paired noisy images, our method synthesizes noise using clean images and factors that affect noise characteristics, such as easily obtainable parameters like camera type and ISO settings, making it applicable to various fields where obtaining noisy-clean image pairs is not feasible. In our experiments, our NM-FlowGAN outperforms other baselines in the sRGB noise synthesis task. Moreover, the denoising neural network trained with synthesized image pairs from our model shows superior performance compared to other baselines. Our code is available at: \url{https://github.com/YoungJooHan/NM-FlowGAN}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
