Point Cloud Resampling via Hypergraph Signal Processing

Three-dimensional (3D) point clouds are important data representations in visualization applications. The rapidly growing utility and popularity of cloud processing strongly motivate a plethora research activities on large-scale feature extraction. In this work, we investigate resampling based hypergraph signal (HGSP). We develop novel method to extract sharp object features reduce the size representation. By directly estimating spectrum stationary processing, design spectral kernel-based filter capture high-dimensional interactions among nodes better preserve surface outlines. Experimental results validate effectiveness representing clouds, demonstrate robustness proposed algorithm under noise.