Computing 3D Object Parts from Similarities Among Object Views
Abstract
The following shape segmentation problem is addressed: find the part decomposition of a 3D object that accounts for an observed pattern of similarities among several of the object's views. This represents the inverse, ill-posed version of the direct problem of computing perceptual similarities among object views when the object parts are known. The problem is solved by inverting a proposed model for the direct similarity-from-parts problem by resorting to regularization techniques. The algorithm takes as input the geometry of the object (given as a triangular mesh), the camera positions corresponding to the rest views, and the perceptual similarities among the test views. The output of the algorithm is a segmentation of the surface of the object into connected regions, i.e., parts.
Cite
Text
Cutzu. "Computing 3D Object Parts from Similarities Among Object Views." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854752Markdown
[Cutzu. "Computing 3D Object Parts from Similarities Among Object Views." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/cutzu2000cvpr-computing/) doi:10.1109/CVPR.2000.854752BibTeX
@inproceedings{cutzu2000cvpr-computing,
title = {{Computing 3D Object Parts from Similarities Among Object Views}},
author = {Cutzu, Florin},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2000},
pages = {2095-2100},
doi = {10.1109/CVPR.2000.854752},
url = {https://mlanthology.org/cvpr/2000/cutzu2000cvpr-computing/}
}