MAXIMUM-A-POSTERIORI ESTIMATION FOR GLOBAL SPATIAL COHERENCE RECOVERY BASED ON MATTING LAPLACIAN

Abstract

Global spatial coherence is an important criterion in the performance evaluation of many image applications, such as image segmentation, image enhancement, depth estimation, motion estimation, and many others. In this paper, we treat the recovery of spatial coherence as a Maximum-A-Posteriori (MAP) estimation problem, with a generalized spatial-coherence prior model based on Matting Laplacian (ML) matrix. Besides, to enhance computational efficiency, a cell-based Matting-Laplacian (CML) framework is further proposed. In our experiments, we demonstrate that the proposed approach can greatly improve the spatial coherence of the output results in variant applications, like the shape-from-focus process and the SIFT-flow refinement process.