Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks
This addresses a specific issue for photographers and users capturing images of screens, offering an incremental improvement in image restoration.
The paper tackles the problem of removing moiré patterns from photos of digital screens, which degrade visual quality, by introducing a multiresolution fully convolutional network that achieves state-of-the-art performance on a new large-scale dataset of over 100,000 image pairs.
Digital cameras and mobile phones enable us to conveniently record precious moments. While digital image quality is constantly being improved, taking high-quality photos of digital screens still remains challenging because the photos are often contaminated with moiré patterns, a result of the interference between the pixel grids of the camera sensor and the device screen. Moiré patterns can severely damage the visual quality of photos. However, few studies have aimed to solve this problem. In this paper, we introduce a novel multiresolution fully convolutional network for automatically removing moiré patterns from photos. Since a moiré pattern spans over a wide range of frequencies, our proposed network performs a nonlinear multiresolution analysis of the input image before computing how to cancel moiré artefacts within every frequency band. We also create a large-scale benchmark dataset with $100,000^+$ image pairs for investigating and evaluating moiré pattern removal algorithms. Our network achieves state-of-the-art performance on this dataset in comparison to existing learning architectures for image restoration problems.