Digital 3-D models of real world scenes are important in many applications in defense and beyond. Constructing 3-D models that faithfully capture the complexity of the real world is a difficult problem. A promising approach is automated 3-D modeling based on directly recording the geometry and color of the scene. Current systems suffer of important disadvantages such as inadequate scene coverage due to slow acquisition, lack of immediate feedback on the quality of the acquired 3-D model, restriction to small scenes, and unintuitive operation. In this paper we give an overview of the ModelCamera automated indoor 3-D modeling project at Purdue University, and we present novel research results and their implementation. The ModelCamera is designed to handle the challenging “inside-looking-out ” 3-D modeling case of large, room-sized scenes. The system is interactive, it provides immediate feedback to the operator, it is efficient, and the resulting 3-D model supports rendering the 3-D scene photorealistically at interactive rates, as needed by applications such as virtual training. ABOUT THE AUTHORS Voicu Popescu is an associate professor of computer science at Purdue University. His research interests