This paper presents a novel mesh denoising and smoothing method. We first estimate the principal curvatures and mesh saliency value of each vertex of the mesh, the uniform principal curvatures of a vertex is then calculated based on the weighted average of local mesh saliency values. The weighted bi-cubic Bezier surface is used to fit the neighborhood of a vertex by the least square method, and the new vertex position is obtained by adjusting the parameters of the local fitting surface. Experiments show that the smoothing method has the following advantages. (1). It can preferably keep the geometry feature of the original mesh model. (2). It can prevent the volume shrinkage of mesh efficiently. (3). The method can attain the smoothing boundaries of non-closed mesh model.