Utilizing Symmetry in the Reconstruction of Three-Dimensional Shape from Noisy Images
Abstract
In previous applications, bilateral symmetry of objects was used either as a descriptive feature in domains such as recognition and grasping, or as a way to reduce the complexity of structure from motion. In this paper we propose a novel application, using the symmetry property to “symmetrize” data before and after reconstruction. We first show how to compute the closest symmetric 2 D and 3 D configurations given noisy data. This gives us a symmetrization procedure, which we apply to images before reconstruction, and which we apply to the 3 D configuration after reconstruction. We demonstrate a significant improvement obtained with real images. We demonstrate the relative merits of symmetrization before and after reconstruction using simulated and real data.
Cite
Text
Zabrodsky and Weinshall. "Utilizing Symmetry in the Reconstruction of Three-Dimensional Shape from Noisy Images." European Conference on Computer Vision, 1994. doi:10.1007/3-540-57956-7_43Markdown
[Zabrodsky and Weinshall. "Utilizing Symmetry in the Reconstruction of Three-Dimensional Shape from Noisy Images." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/zabrodsky1994eccv-utilizing/) doi:10.1007/3-540-57956-7_43BibTeX
@inproceedings{zabrodsky1994eccv-utilizing,
title = {{Utilizing Symmetry in the Reconstruction of Three-Dimensional Shape from Noisy Images}},
author = {Zabrodsky, Hagit and Weinshall, Daphna},
booktitle = {European Conference on Computer Vision},
year = {1994},
pages = {403-419},
doi = {10.1007/3-540-57956-7_43},
url = {https://mlanthology.org/eccv/1994/zabrodsky1994eccv-utilizing/}
}