Shedding light on stereoscopic segmentation

@inproceedings{citeulike:1373091, 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.}, author = {Jin, Hailin and Cremers, D. and Yezzi, A. J. and Soatto, S. }, citeulike-article-id = {1373091}, journal = {Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on}, keywords = {lighting, segmentation, sfs, stereo}, pages = {I-36--I-42 Vol.1}, posted-at = {2007-06-08 16:50:31}, priority = {2}, title = {Shedding light on stereoscopic segmentation}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1315011}, volume = {1}, year = {2004} }

TY - CONF ID - citeulike:1373091 L3 - citeulike-article-id:1373091 TI - Shedding light on stereoscopic segmentation JF - Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on VL - 1 SP - I-36 EP - I-42 Vol.1 N2 - 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. KW - lighting KW - segmentation KW - sfs KW - stereo AU - Jin, Hailin AU - Cremers, D AU - Yezzi, AJ AU - Soatto, S PY - 2004/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1315011 ER -