This paper focuses on addressing the issue of image demoireing. Unlike the large volume of existing studies that rely on learning from paired real data, we attempt to learn a demoireing model from unpaired real data, i.e., moire images associated with irrelevant clean images. The proposed method, referred to as Unpaired Demoireing (UnDeM), synthesizes pseudo moire images from unpaired datasets, generating pairs with clean images for training demoireing models. To achieve this, we divide real moire images into patches and group them in compliance with their moire complexity. We introduce a novel moire generation framework to synthesize moire images with diverse moire features, resembling real moire patches, and details akin to real moire-free images. Additionally, we introduce an adaptive denoise method to eliminate the low-quality pseudo moire images that adversely impact the learning of demoireing models. We conduct extensive experiments on the commonly-used FHDMi and UHDM datasets. Results manifest that our UnDeM performs better than existing methods when using existing demoireing models such as MBCNN and ESDNet-L. Code: https://github.com/zysxmu/UnDeM

翻译：本文聚焦于图像去摩尔纹问题。与现有大量依赖配对真实数据学习的研究不同，我们尝试从非配对真实数据（即摩尔纹图像与无关的干净图像）中学习去摩尔纹模型。所提出的方法称为非配对去摩尔纹（UnDeM），通过从非配对数据集中合成伪摩尔纹图像，生成与干净图像的配对样本以训练去摩尔纹模型。为此，我们将真实摩尔纹图像分割为图像块，并按其摩尔纹复杂度进行分组。我们引入了一种新颖的摩尔纹生成框架，合成具有多样化摩尔纹特征（类似真实摩尔纹块）以及细节（类似真实无摩尔纹图像）的摩尔纹图像。此外，我们提出了一种自适应去噪方法，用于剔除对去摩尔纹模型学习产生不利影响的低质量伪摩尔纹图像。我们在广泛使用的FHDMi和UHDM数据集上进行了大量实验。结果表明，在结合现有MBCNN和ESDNet-L等去摩尔纹模型时，我们的UnDeM方法性能优于现有方法。代码：https://github.com/zysxmu/UnDeM