A Modified Laplacian Smoothing Approach with Mesh Saliency

摘要

A good saliency map captures the locally sharp features effectively. So a number of tasks in graphics can benefit from a computational model of mesh saliency. Motivated by the conception of Lee's mesh saliency and its successful application to mesh simplification and viewpoint selection, we modified Laplacian smoothing operator with mesh saliency. Unlike the classical Laplacian smoothing, where every new vertex of the mesh is moved to the barycenter of its neighbors, we set every new vertex position to be the linear interpolation between its primary position and the barycenter of its neighbors. We have shown how incorporating mesh saliency with Laplacian operator can effectively preserve most sharp features while denoising the noisy model. Details of our modified Laplacian smoothing algorithm are discussed along with the test results in this paper.