Nonlocal segmentation of point clouds with graphs

In this paper, we propose a nonlocal approach based on graphs to segment raw point clouds as a particular class of graph signals. Using the framework of Partial difference Equations (PdEs), we propose a transcription on graphs of recent continuous global active contours along with a minimization algorithm. To apply it on point clouds, we show how to represent a point cloud as a graph weighted with patches. Experiments show the benefits of the approach on raw colored point clouds obtained from real scans.