Removing moiré patterns from single images.

Interference between the grids of the camera sensor and the screen cause moiré patterns to always appear on photographs captured from a screen, significantly affecting people’s ability to review images. We propose a novel method to remove such a screen moiré pattern from a single image. We characterize the degraded image as a composition of two layers: the latent layer and the moiré pattern layer. Because the screen moiré pattern is global and content-independent, we regard it as a group of sublayers, and we find that each sublayer after the shear transformation has a low-rank property. Combined with the piecewise constant feature of the latent layer, a convex model is proposed to solve the demoiréing problem. Experiments on synthetic and real data demonstrate its feasibility and efficiency.