This demonstration presents the methods for 3D scene geometry recovery/refinement and pose estimation from motion imagery in two representative scenarios. First, we present the method for pose estimation and scene geometry recovery from extended sequences without a prior knowledge of the scene. Second, we discuss how to recover camera poses when a rough scene model is provided. We show how to extend and refine the scene model using the recovered poses. Finally, we present applications of above techniques for 3D imagery manipulation such as enhanced visualization for the video and 3D insertion of synthetic objects in the imagery.