Restoration of Recaptured Screen Images With a Divide and Conquer Strategy

Moiré patterns in recaptured screen images are image defects that can affect image quality to an extreme extent. Different from other image defects, moiré artefacts can vary greatly in scales, colours and shapes. Such moiré patterns mix with image content and disturb image features of different scales in different ways, making moiré pattern removal a challenging task. In this paper, we present a novel divide-and-conquer strategy to solve the problem. In the divide stage, we innovatively decompose images into different layers, as well as into structure components and detail components. Then in the conquer stage, guided by the layers retrieved from the divide stage, we can restore coarse and fine image components independently, which greatly improve the demoiréing performance. Our strategy outperforms state-of-arts in both quantitative and qualitative evaluations.