Wavelet-Based Dual-Branch Network for Image Demoiréing

When smartphone cameras are used to take photos of digital screens, usually moiré patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoiréing. Existing image restoration methods working in the RGB domain have difficulty in distinguishing moiré patterns from true scene texture. Unlike these methods, our network removes moiré patterns in the wavelet domain to separate the frequencies of moiré patterns from the image content. The network combines dense convolution modules and dilated convolution modules supporting large receptive fields. Extensive experiments demonstrate the effectiveness of our method, and we further show that WDNet generalizes to removing moiré artifacts on non-screen images. Although designed for image demoiréing, WDNet has been applied to two other low-level vision tasks, outperforming state-of-the-art image deraining and deraindrop methods on the Rain100h and Raindrop800 data sets, respectively.