Enforcing image consistency in multiple 3-D object modelling

Matthew Grum, Adrian G. Bors

Abstract: In this paper we present a new approach for modelling multiple object scenes using images taken from various viewpoints. The voxel representation produced by the space carving is used for estimating the parameters of radial basis function functions (RBFs). A new methodology is proposed for correcting the modelling errors within the RBF framework, by enforcing consistency with the input images by matching along epipolar lines, and enforcing silhouette constraints using the visual hull. The proposed methodology is applied on two datasets consisting of several objects while providing quantitative and qualitative assessment.