In this paper, we present a method for automatically creating a 3D model of a scene from a set of range images obtained from unknown viewpoints. Existing 3D modeling approaches require manual interaction or rely on mechanical methods to estimate the viewpoints. Given a set of range images (views), we use a surface matching system to exhaustively register all pairs of views. The results are verified for consistency, but some incorrect matches may be locally undetectable and correct matches may be missed. We then construct a consistent model from these potentially faulty matches using a global consistency criterion to eliminate incorrect, but locally consistent, matches. The procedure is demonstrated through an application called hand-held modeling, in which a 3D model is automatically created by scanning an object held in a person's hand.
Daniel F. Huber