Structure from Motion for Scenes Without Features

CVPR 2003 pp. 525-532

doi:10.1109/CVPR.2003.1211399 /cvpr/2003/yezzi2003cvpr-structure/

Abstract

We describe an algorithm for reconstructing the 3D (three-dimensional) shape of the scene and the relative pose of a number of cameras from a collection of images under the assumption that the scene does not contain photometrically distinct "features". We work under the explicit assumption that the scene is made of a number of smooth surfaces that radiate constant energy isotropically in all directions, and setup a region-based cost functional that we minimize using local gradient flow techniques.

PDF CVPR Semantic Scholar

Cite

Text

Yezzi and Soatto. "Structure from Motion for Scenes Without Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211399

Markdown

[Yezzi and Soatto. "Structure from Motion for Scenes Without Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/yezzi2003cvpr-structure/) doi:10.1109/CVPR.2003.1211399

BibTeX

@inproceedings{yezzi2003cvpr-structure,
  title     = {{Structure from Motion for Scenes Without Features}},
  author    = {Yezzi, Anthony J. and Soatto, Stefano},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {525-532},
  doi       = {10.1109/CVPR.2003.1211399},
  url       = {https://mlanthology.org/cvpr/2003/yezzi2003cvpr-structure/}
}