Abstract
A method for reconstructing 3D rational B-spline surfaces from multiple views is proposed. Given corresponding features in multiple views, though not necessarily visible in all views, the surface is reconstructed. First 2D B-spline patches are fit to each view. The 3D B-spline and projection matrices can then be extracted from the 2D B-splines using factorization methods. The surface fit is then further refined via an iterative procedure. Finally, a hierarchal fitting scheme is proposed to allow modeling of complex surfaces by means of knot insertion. Experiments with real imagery demonstrate the efficacy of the approach.