HOME		Research		Publications

Non-rigid 3D shape recovery using stereo factorization

We address the problem of recovering 3D nonrigid structure from a sequence of images taken with a stereo pair. We have extended the existing non-rigid factorization algorithms to the stereo camera case and presented an algorithm to decompose the measurement matrix into the motion of the left and right cameras and the 3D shape, represented as a linear combination of basis-shapes.

Stereo Factorization The proposed linear method is able to reconstruct a reliable flexible 3D shape given an uncalibrated stereo setup. As a result we can infer the structure in the absence of rigid motion of the observed object. Our experiments with real data show that improved reconstructions can be achieved using this method.

Non-Linear Optimization for Stereo Factorization We perform a non-linear optimization step that minimizes image reprojection error and impose the correct structure to the motion matrix. While this optimization step is proposed for the stereo camera case, it can be readily applied to the case of non-rigid structure recovery using a monocular video sequence.

Updated Feb 2005 by Alessio Del Bue