PROJECT TITLE :

Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks - 2018

ABSTRACT:

Digital cameras and mobile phones enable us to conveniently record precious moments. Whereas digital image quality is continually being improved, taking high-quality photos of digital screens still remains challenging because the photos are often contaminated with moiré patterns, a results of the interference between the pixel grids of the camera sensor and the device screen. Moiré patterns will severely damage the visual quality of photos. However, few studies have aimed to resolve this downside. In this Project, we introduce a novel multiresolution fully convolutional network for automatically removing moiré patterns from photos. Since a moiré pattern spans over a wide selection of frequencies, our proposed network performs a nonlinear multiresolution analysis of the input image before computing a way to cancel moiré artefacts at intervals every frequency band. We also produce a giant-scale benchmark data set with 1 0zero 000 + image pairs for investigating and evaluating moiré pattern removal algorithms. Our network achieves the state-of-the-art performance on this information set as compared to existing learning architectures for image restoration issues.