The popularity of smartphones with digital cameras makes photographing using smartphones an important daily activity. Moiré patterns can easily appear when shooting objects with rich textures, such as computer screens, and will severely degrade the image quality. Image demoiréing is an important image restoration task that aims to remove moiré patterns and reveal the underlying clean image. Two key properties of moiré patterns—the widely distributed frequency spectrum and the dynamic nature of moiré textures—challenge the image demoiréing task. In this paper, we propose an improved Multi-scale convolutional network with Dynamic feature encoding for image DeMoiréing (MDDM+). We design two schemes in our network to respectively attack the broad frequency spectrum and the dynamic texture of moiré: a multi-scale structure to process images at different spatial resolutions and a dynamic feature encoding module to encode the texture dynamically. To capture more moiré and texture information from different frequencies, we further propose a novel $L_1$ wavelet loss used to train our model. Extensive experiments on two benchmarks show that our proposed image demoiréing network can outperform the state of the arts in terms of fidelity as well as perception.

带有数码相机的智能手机的普及使使用智能手机拍照成为一项重要的日常活动。当拍摄具有丰富纹理的物体（例如计算机屏幕）时，莫尔图案很容易出现，并且会严重降低图像质量。图像去污是一项重要的图像恢复任务，旨在消除波纹图案并揭示基本的干净图像。莫尔图案的两个关键特性-广泛分布的频谱和莫尔纹理的动态性质-挑战了图像去马赛克的任务。在本文中，我们提出了一种改进的具有动态特征编码的多尺度卷积网络，用于图像去噪（MDDM +）。我们在网络中设计了两种方案来分别攻击宽频谱和莫尔条纹的动态纹理：一种用于处理不同空间分辨率的图像的多尺度结构，以及用于对纹理进行动态编码的动态特征编码模块。为了从不同频率捕获更多的莫尔条纹和纹理信息，我们进一步提出了一种新颖的方法${\mathrm{大号}}_{\mathrm{1个}}$小波损失用于训练我们的模型。在两个基准上进行的大量实验表明，我们提出的图像去污网络可以在保真度和感知度方面超越现有技术。