August 2001
Shape and motion recovery is a problem that can be formulated in many different ways. For post-production applications, the main difficulty is to recover precisely the 3D structure and the path of the camera in long image sequences. Our approach states the problem as a parametric estimation problem, that allow to handle heterogeneous information on the system and uncertainties in a Bayesian context. From geometric reduction, we integrate in the scene description various geometric shapes along with geometric relationships. Similarly, the camera motion is modeled on the entire sequence using polynomial curves, which degree is set by model selection. The elements of the scene are tracked along the sequence, then the parameters of the models are estimated in a sequential fashion. We present reconstruction results on various simulated and real sequences, and the method is successfully applied for augmented reality effects.
Pierre-Louis recently joined the SHAPE Lab as a Post-Doc. He did his graduate work at INRIA - Rocquencourt in France, under the supervision of Dr. Jean-Marc Vézien, in the MIRAGES team of Dr. André Gagalowicz. This talk is a summary of his PhD. More information on Pierre-Louis is available at :
Last Updated: July 26, 2001