A Novel Volumetric Shape from Silhouette Algorithm Based on a Centripetal Pentahedron Model

In this paper we present a novel volumetric shape from silhouette algorithm based on a centripetal pentahedron model. The algorithm first partitions the space with a set of infinite triangular pyramids derived from a geodesic sphere. Then the pyramids are cut by silhouettes into a set of pentahedrons, which together constitute the centripetal pentahedron model of the visual hull. This process is accelerated by precomputed polar silhouette graphs (PSGs) and reduced PSGs. Finally a mesh surface model is extracted by marching pentahedrons. Our algorithm has the advantages of robustness, speediness and preciseness.