基于风格解耦的图像去噪
Image Denoising via Style Disentanglement
AI总结：
该研究将噪声视为图像风格，设计损失与网络模块提取并引入无噪声风格，实现像素级噪声与内容解耦，在SIDD、DND等数据集上提升去噪性能并增强可解释性。
摘要：
图像去噪是低层计算机视觉中的一项基础任务。尽管近期基于深度学习的图像去噪方法已经取得令人瞩目的性能，但它们属于黑盒模型，其底层去噪原理仍不明确。本文提出一种新颖的图像去噪方法，同时具备清晰的去噪机制和良好的性能。我们将噪声视为一种图像风格，并通过引入从干净图像中获得的无噪声风格来去除噪声。为此，我们设计了新的损失函数和网络模块，以从含噪图像中提取含噪风格，并从干净图像中提取无噪声风格。无噪声风格会在特征空间中对噪声特征产生低响应激活，而对内容特征产生高响应激活。这促使干净内容与噪声分离，从而有效去除图像中的噪声。不同于基于解耦的图像编辑任务利用风格编辑语义级属性，我们的主要贡献在于通过全局无噪声风格编辑像素级属性。我们在合成噪声去除和真实世界图像去噪数据集（SIDD和DND）上进行了大量实验，从PSNR和SSIM两项指标证明了该方法的有效性。此外，我们通过实验验证该方法具有良好的可解释性。
英文摘要：
Image denoising is a fundamental task in low-level computer vision. While recent deep learning-based image denoising methods have achieved impressive performance, they are black-box models and the underlying denoising principle remains unclear. In this paper, we propose a novel approach to image denoising that offers both clear denoising mechanism and good performance. We view noise as a type of image style and remove it by incorporating noise-free styles derived from clean images. To achieve this, we design novel losses and network modules to extract noisy styles from noisy images and noise-free styles from clean images. The noise-free style induces low-response activations for noise features and high-response activations for content features in the feature space. This leads to the separation of clean contents from noise, effectively denoising the image. Unlike disentanglement-based image editing tasks that edit semantic-level attributes using styles, our main contribution lies in editing pixel-level attributes through global noise-free styles. We conduct extensive experiments on synthetic noise removal and real-world image denoising datasets (SIDD and DND), demonstrating the effectiveness of our method in terms of both PSNR and SSIM metrics. Moreover, we experimentally validate that our method offers good interpretability.
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。
