Robust Fuzzy C-Means and Bilateral Point Clouds Denoising

A point clouds denoising method is presented which combines fuzzy c-means clustering with bilateral filtering approach. Surfaces are reconstructed from unorganized point sets with large-scale noise. Firstly, we delete large-scale noise, partly smooth small-scale noise with improved method of fuzzy c-means clustering. The cluster centers are regarded as the new points. After acquiring new point sets being less noisy, we smooth the remains noise by bilateral point clouds denoising method. The implicit representation of the surface through these new points is then calculated by local and global compactly supported radial basis function (RBF). The experiments show that the large-scale noise will be deleted and the noisy point sets are smoothed well. After clustering and filtering methods, interpolation point choosing of compactly supported RBF provides a robust solution for implicit surface reconstruction from noisy data