Multi-scale creases detection on noisy meshes

We propose a multi-scale approach to detecting creases on noisy meshes. Given a noisy mesh as input, first we generate its discrete multi-scale representation based on an improved anisotropic diffusion method. Then, a method is presented for detecting salient vertices on a noisy mesh by exploiting curvatures estimated at different scales. Finally, creases are generated by connecting curvature extrema points detected on the mesh edges with the salient vertices as end points. During this process, the mesh features are preserved. Experimental results demonstrate that our approach works well on noisy meshes reconstructed from raw scanning data, by showing that geometrically and perceptually salient creases are well detected on noisy meshes.