by Csaba Domokos, Zoltan Kato
Abstract:
This paper is addressing the problem of realigning broken objects without correspondences. We consider linear transformations between the object fragments and present the method through 2D and 3D affine transformations. The basic idea is to construct and solve a polynomial system of equations which provides the unknown parameters of the alignment. We have quantitatively evaluated the proposed algorithm on a large synthetic dataset containing 2D and 3D images. The results show that the method performs well and robust against segmentation errors. We also present experiments on 2D real images as well as on volumetric medical images applied to surgical planning.
Reference:
Csaba Domokos, Zoltan Kato, Affine puzzle: Realigning deformed object fragments without correspondences, In Proceedings of European Conference on Computer Vision (Kostas Daniilidis, Petros Maragos, Nikos Paragios, eds.), volume 6312 of Lecture Notes in Computer Science, Crete, Greece, pp. 777-790, 2010, Springer.
Bibtex Entry:
@string{eccv="Proceedings of European Conference on Computer Vision"}
@string{lncs="Lecture Notes in Computer Science"}
@string{springer="Springer"}
@INPROCEEDINGS{Domokos-Kato2010,
author = {Domokos, {Cs}aba and Kato, Zoltan},
title = {Affine puzzle: Realigning deformed object fragments without correspondences},
booktitle = eccv,
year = {2010},
editor = {Daniilidis, Kostas and Maragos, Petros and Paragios, Nikos},
volume = {6312},
series = lncs,
pages = {777--790},
address = {Crete, Greece},
month = sep,
publisher = springer,
abstract = {This paper is addressing the problem of realigning broken objects
without correspondences. We consider linear transformations between
the object fragments and present the method through 2D and 3D affine
transformations. The basic idea is to construct and solve a polynomial
system of equations which provides the unknown parameters of the
alignment. We have quantitatively evaluated the proposed algorithm
on a large synthetic dataset containing 2D and 3D images. The results
show that the method performs well and robust against segmentation
errors. We also present experiments on 2D real images as well as
on volumetric medical images applied to surgical planning.},
pdf = {papers/eccv2010.pdf}
}