Unpaired Image Demoireing Based on Cyclic Moire Learning

Abstract

We propose an end-to-end unsupervised learning approach to image demoireing based on cyclic moire learning. The proposed cyclic moire learning consists of the moire learning network and demoireing network. The moire learning network generates moire images to construct a paired set of moire and clean images. Then, the demoireing network is trained using the generated paired dataset to remove moire artifacts. Further, the moire learning network and the demoireing network are integrated together to be trained in an end-to-end manner. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art unsupervised image restoration algorithms.