Image Mosaicing for Tete-Reality Applications

This paper presents some techniques for automatically deriving realistic 2-D scenes and 3-D geometric models from video sequences. These techniques can be used to build environments and 3-D models for virtual reality application based on recreating a true scene, i.e., tele-realityapplications. The fundamental technique used in this paper is imagemosaicing, i.e., the automatic alignment of multiple images into larger aggregates which are then used to represent portions of a 3-D scene. The paper first examines the easiest problems, those of flat scene and panoramic scene mosaicing. It then progresses to more complicated scenes with depth, and concludes with full 3-D models. The paper also discusses a number of novel applications based on tele-reality technology.