Visual 3D Modeling from Images
Speaker: Marc Pollefeys , UNC Chapel Hill
Date: November 25 2002
In this talk a complete approach to reconstruct visual 3D models from camera images is presented. The approach can deal with uncalibrated image sequences acquired with a hand-held camera. Based on tracked or matched features the relation between multiple views are computed. >From this both the structure of the scene and the motion of the camera are retrieved. The ambiguity on the reconstruction is restricted from projective to metric through self-calibration. A flexible multi-view stereo matching scheme is used to obtain a dense estimation of the surface geometry. From the computed data different types of visual models are constructed. Both 3D surface models and lightfield repre- sentations can be constructed. The recovered information can also be used to augment video footage with virtual object. The proposed ap- proach will also be illustrated with applications ranging from archae- ology to planetary rover control.
Marc Pollefeys is an Assistant Professor of Computer Science at the University of North Carolina at Chapel Hill. Previously he was a postdoctoral researcher at the Katholieke Universiteit Leuven in Belgium, where he also received his M.S. and Ph.D. degrees in 1994 and 1999, respectively. Dr. Pollefeys joined the faculty at UNC-Chapel Hill in July 2002. His main area of research is computer vision, more specifically multi-view geometry, structure from motion, (self-)calib- ration, stereo, image-based rendering and applications. One of his main research goals is to develop flexible approaches to capture visual representations of real world objects, scenes and events. Dr. Pollefeys has received several prizes for his research, including the prestigious Marr prize at ICCV '98. He is the author or co-author of more than 70 technical papers. He has organized workshops and courses at major vision and graphics conferences and has served on the program committees of many conferences. He is a regular reviewer for most of the major vision, graphics and photogrammetry journals.
See other events that are part of AI Colloquium Series Fall 2002
See other events happening in November 2002