In this paper, we study the problem of mesh denoising for improving the single pass surface estimation on normals and curvature tensors. We focus mainly on the engineering objects represented as dense triangle meshes. In particular, a two run nonlinear diffusion algorithm based on optimal estimation theory is proposed to adoptively filter out the undesired discontinuities introduced by noise while preserving the underlying features. We show that the proposed filter can successfully improve the local surface estimates while preserving the desired features in terms of tangential and curvature discontinuities.