A Gaussian graphical model based approach for image inpainting

Abstract

Digital image inpainting means reconstruction of small damaged portions of images. In this paper, we propose an algorithm for digital image inpainting which is a combination of pixel-diffusing technique and a user interaction mechanism. In our approach, the user manually specifies important missing structure information by extending a few curves or line segments from the known region to the unknown regions. Our approach synthesizes image patches along these user-specified curves in the unknown region using patches selected around the curves in the known region. We call this step as structure propagation. After completing structure propagation, we fill in the remaining unknown regions using Gaussian Graphical Model which is MRF based. The experiment results show that our approach is reasonable and efficient. In addition, our method is very simple to be implemented and fast. © 2012 Springer-Verlag GmbH.