Stochastic Poisson Surface Reconstruction
Silvia Sellán, Alec Jacobson
Abstract
We introduce a statistical extension of the classic Poisson Surface Reconstruction algorithm for recovering shapes from 3D point clouds. Instead of outputting an implicit function, we represent the reconstructed shape as a modified Gaussian Process, which allows us to conduct statistical queries (e.g., the likelihood of a point in space being on the surface or inside a solid). We show that this perspective: improves PSR's integration into the online scanning process, broadens its application realm, and opens the door to other lines of research such as applying task-specific priors.
Topics & Concepts
Point processSurface reconstructionComputer scienceSurface (topology)Poisson distributionPrior probabilityPoint cloudExtension (predicate logic)AlgorithmGaussianPoisson point processFunction (biology)Point (geometry)Gaussian processMathematicsArtificial intelligenceGeometryBayesian probabilityStatisticsEvolutionary biologyBiologyPhysicsQuantum mechanicsProgramming language3D Shape Modeling and AnalysisComputer Graphics and Visualization TechniquesAdvanced Vision and Imaging