ML Anthology

Using Symmetries for Analysis of Shape from Contour

Fatih Ulupinar, Ramakant Nevatia
ICCV 1988 pp. 414-426
doi:10.1109/CCV.1988.590018 /iccv/1988/ulupinar1988iccv-using/

Abstract

Inference of 3-D shape from 2-D contours in a single image is an important problem in machine vision. We survey classes of techniques proposed in the past and provide a critical analysis. We propose two kinds of symmetries in figures, which we call parallel and mirror symmetries, give significant information about surface shape for a variety of objects. We show the constraints imposed by these symmetries and how to use them to infer 3-D shape. Our method is applicable to any zero-gaussian curvature surface, and also to a variety of doubly curved surfaces. One of our mathematical results is that for a cone, the surface shape can be constructed uniquely under very simple assumptions. We also show some preliminary results on extraction of symmetries from real images.

ICCV Semantic Scholar

Cite

Text

Ulupinar and Nevatia. "Using Symmetries for Analysis of Shape from Contour." IEEE/CVF International Conference on Computer Vision, 1988. doi:10.1109/CCV.1988.590018

Markdown

[Ulupinar and Nevatia. "Using Symmetries for Analysis of Shape from Contour." IEEE/CVF International Conference on Computer Vision, 1988.](https://mlanthology.org/iccv/1988/ulupinar1988iccv-using/) doi:10.1109/CCV.1988.590018

BibTeX

@inproceedings{ulupinar1988iccv-using,
  title     = {{Using Symmetries for Analysis of Shape from Contour}},
  author    = {Ulupinar, Fatih and Nevatia, Ramakant},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1988},
  pages     = {414-426},
  doi       = {10.1109/CCV.1988.590018},
  url       = {https://mlanthology.org/iccv/1988/ulupinar1988iccv-using/}
}