Putting the Pieces Together: Regularized Multi-Part Shape Matching
Abstract
Multi-part shape matching is an important class of problems, arising in many fields such as computational archaeology, biology, geometry processing, computer graphics and vision. In this paper, we address the problem of simultaneous matching and segmentation of multiple shapes. We assume to be given a reference shape and multiple parts partially matching the reference. Each of these parts can have additional clutter, have overlap with other parts, or there might be missing parts. We show experimental results of efficient and accurate assembly of fractured synthetic and real objects.
Cite
Text
Litany et al. "Putting the Pieces Together: Regularized Multi-Part Shape Matching." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33863-2_1Markdown
[Litany et al. "Putting the Pieces Together: Regularized Multi-Part Shape Matching." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/litany2012eccv-putting/) doi:10.1007/978-3-642-33863-2_1BibTeX
@inproceedings{litany2012eccv-putting,
title = {{Putting the Pieces Together: Regularized Multi-Part Shape Matching}},
author = {Litany, Or and Bronstein, Alexander M. and Bronstein, Michael M.},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {1-11},
doi = {10.1007/978-3-642-33863-2_1},
url = {https://mlanthology.org/eccv/2012/litany2012eccv-putting/}
}