A new weighted normal-based filter for 3D mesh denoising

In this paper, we propose a normal based filtering method for 3D mesh denoising. For this purpose, we compute the new triangle normal vectors by using a weighted sum of the average (smoothness) and the myriad (sharpness) filters in each neighborhood. These weights, that reflect the degree of the surface sharpness, are calculated according to the statistical distribution of the angles between the normal vectors of the triangles. The histogram of the angles between surface normal vectors is accurately fitted by the well known Cauchy distribution. Here, we justify the use of the myriad filter whose estimated value represents the optimum of the location parameter of the investigated distribution. Once the whole of the mesh normal vectors are filtered, the vertices positions are updated via the most used method in mesh denoising frameworks. We test the proposed method on synthetic and real scanned objects. To evaluate the performance, we use three errors metrics that are the vertex based error, the normal based error and the Hausdorff distance. Results show the superiority of our method and its efficiency is compared with some existing methods in the literature.