Image completion has been widely used to repair damaged regions of a given digital image in a visually plausible way. However, it is difficult to infer appropriate information, meanwhile keep globally coherent just from the origin image when its critical parts are missing. To address this problem, we propose a novel layer-divided image completion scheme, which contains two major steps. First, we extract foregrounds of both target image and source image, and then we apply a guided Poisson surface reconstruction technique to complete the target foreground according to parameters obtained from optimal-matching calculation. Second, to fill the remaining damaged part, a related exemplar-based image completion algorithm is further devised. Several experiments and comparisons show the effectiveness and robustness of our proposed algorithm.