|
Published Articles >> Table of Contents >> Abstract
2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 1
pp. 36-42
Shedding Light on Stereoscopic Segmentation
Hailin Jin, University of California at Los Angeles
Daniel Cremers, University of California at Los Angeles
Anthony J. Yezzi, Georgia Institute of Technology
Stefano Soatto, University of California at Los Angeles
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2004.233
Send link to a friend
| Abstract |
|
We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can be thought of as extending classical multi-view stereo to cases where point correspondence cannot be established, or extending classical shape from shading to the case of multiple views with unknown light sources. We show that a first naive formalization of this problem yields algorithms that are numerically unstable, no matter how close the initialization is to the true geometry. We then propose a computational scheme to overcome this problem, resulting in provably stable algorithms that converge to (local) minima of the cost functional. Although we restrict our attention to Lambertian objects with uniform albedo, extensions of our framework are conceivable.
|
 Additional Information
|
Citation:
Hailin Jin, Daniel Cremers, Anthony J. Yezzi, Stefano Soatto,
"Shedding Light on Stereoscopic Segmentation,"
cvpr,
pp. 36-42,
2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 1,
2004
|
|
