Proceedings of the NATO Meeting : Confluence of Computer Vision and Computer Graphics, August 1999., Ljubljana, Slovenia.
The problem of building virtual models from sensor data increases in importance as powerful graphics rendering hardware becomes widespread. Model building stands at the interface between computer vision and computer graphics, and researchers from both areas have made contributions. We believe that only by a systematic review of the remaining open research question can further progress be made. This paper is an attempt at providing such a review. First, we describe the basic steps in the model building pipeline. Then we discuss the open problems that remain in each step. Finally, we describe some overall research themes that we believe should guide further work in this area.