3D structure and motion from images
		   
			Marc Pollefeys

	      Katholieke Universiteit Leuven, Belgium

Abstract:

In this talk a complete system to build visual models from camera
images is presented.  The system 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 representations can be constructed.  The recovered
information can also be used to augment video footage with virtual
object.  The proposed approach will also be illustrated with
applications ranging from archaeology to plantary rover control.