Interference between overlapping gird patterns creates moire patterns, degrading the visual quality of an image that captures a screen of a digital display device by an ordinary digital camera. Removing such moire patterns is challenging due to their complex patterns of diverse sizes and color distortions. Existing approaches mainly focus on filtering out in the spatial domain, failing to remove a large-scale moire pattern. In this paper, we propose a novel model called FPANet that learns filters in both frequency and spatial domains, improving the restoration quality by removing various sizes of moire patterns. To further enhance, our model takes multiple consecutive frames, learning to extract frame-invariant content features and outputting better quality temporally consistent images. We demonstrate the effectiveness of our proposed method with a publicly available large-scale dataset, observing that ours outperforms the state-of-the-art approaches, including ESDNet, VDmoire, MBCNN, WDNet, UNet, and DMCNN, in terms of the image and video quality metrics, such as PSNR, SSIM, LPIPS, FVD, and FSIM.

翻译：重叠网格图案之间的相互干扰会产生摩尔纹图案，从而降低普通数码相机拍摄数字显示设备屏幕时的图像视觉质量。由于摩尔纹图案具有尺寸多样和色彩畸变的复杂特性，去除这类图案极具挑战性。现有方法主要专注于在空间域进行滤波处理，但无法有效去除大尺度摩尔纹图案。本文提出一种名为FPANet的新型模型，该模型在频率域和空间域同时学习滤波器，通过去除不同尺寸的摩尔纹图案来提升图像修复质量。为进一步增强效果，我们的模型采用多连续帧输入，学习提取帧不变内容特征，并输出质量更高、时间一致性更强的图像。我们利用公开的大规模数据集验证了所提方法的有效性，结果表明，在PSNR、SSIM、LPIPS、FVD和FSIM等图像与视频质量指标上，我们的方法优于包括ESDNet、VDmoire、MBCNN、WDNet、UNet和DMCNN在内的现有最优方法。