Structure and Motion from a Sparse Set of Views
Mi-Suen Lee*, Gerard Medioni* and Rachid Deriche**
*Institute for Robotics and Intelligent Systems, University of Southern California, USA
**INRIA-Sophia Antipolis, France
Abstract
We address the problem of acquiring 3D information of an object from multiple images. While long image sequence contains more clues about the motion of the object in the scene, it provides no more information about the object than a few images that show various aspect of the object. We propose an algorithm that uses nonlinear least squares fitting to compute structure and motion from a
small number of images in which various aspect of an object is shown. The location of features that show up in different aspect of the object are computed with respected to a
single reference frame. As with all other nonlinear problems, our algorithm requires initial guesses. While we
adopted an analytical method in the initialization stage, experimental results on synthetic data and real images show
that the quality of our solution does not degrade with the
accuracy of the initial guesses.
Key Words:
Structure from motion, Motion analysis, non-linear least squares fitting
Example Result:
Images of the Renault part :
Recovered model:
3D points
Recovered Model in Motion
(requires a Geomview 3-D browser)
Rendered views
The Paper:
Click here to get the PDF file of the paper
Maintained by Mi Suen Lee