论文标题
图像与可学习的带通滤波器进行示范
Image Demoireing with Learnable Bandpass Filters
论文作者
论文摘要
图像演示是一项多方面的图像恢复任务，涉及纹理和颜色恢复。在本文中，我们提出了一种新型的多尺度带通卷积神经网络（MBCNN）来解决这个问题。作为端到端的解决方案，MBCNN分别解决了两个子问题。对于纹理恢复，我们提出了一个可学习的带通滤波器（LBF），以了解Moire纹理去除的先验频率。对于颜色恢复，我们提出了一个两步的音调映射策略，该策略首先应用了全局音调映射以校正全局颜色，然后对每个像素的颜色进行局部微调。通过消融研究，我们证明了MBCNN不同成分的有效性。两个公共数据集的实验结果表明，我们的方法的表现优于最先进的方法（在PSNR方面超过2DB）。
Image demoireing is a multi-faceted image restoration task involving both texture and color restoration. In this paper, we propose a novel multiscale bandpass convolutional neural network (MBCNN) to address this problem. As an end-to-end solution, MBCNN respectively solves the two sub-problems. For texture restoration, we propose a learnable bandpass filter (LBF) to learn the frequency prior for moire texture removal. For color restoration, we propose a two-step tone mapping strategy, which first applies a global tone mapping to correct for a global color shift, and then performs local fine tuning of the color per pixel. Through an ablation study, we demonstrate the effectiveness of the different components of MBCNN. Experimental results on two public datasets show that our method outperforms state-of-the-art methods by a large margin (more than 2dB in terms of PSNR).
