A cascaded approach for feature-preserving surface mesh denoising

Mesh denoising is crucial for improving noisy meshes acquired from scanning devices and digitization processes. This paper proposes a general, robust approach for mesh denoising by using a combination of bilateral filtering, feature recognition, anisotropic neighborhood searching, and surface fitting and projection techniques. Motivated by the bilateral filtering from image processing applications, we develop a new bilateral filter operating on the normal vector fields of the mesh. Then, we detect mesh features and classify mesh vertices into non-feature vertices and feature vertices. The corresponding anisotropic neighborhoods for each vertex are searched by constructing a weighted dual graph, over which biquadratic Bezier surface patches are fitted and projected. The projection points are averaged to update each vertex of the mesh. The steps above are repeated iteratively until convergence, i.e., the Hausdorff distance between two sequential denoised meshes is less than a pre-defined threshold. A number of examples presented in the paper demonstrate that our method generally yields visually and numerically better denoising results, compared with the state-of-the-art methods.