ML Anthology

Shape Ambiguities in Structure from Motion

Richard Szeliski, Sing Bing Kang
ECCV 1996 pp. 709-721
doi:10.1007/BFB0015580 /eccv/1996/szeliski1996eccv-shape/

Abstract

This paper examines the fundamental ambiguities and uncertainties inherent in recovering structure from motion. By examining the eigenvectors associated with null or small eigenvalues of the Hessian matrix, we can quantify the exact nature of these ambiguities and predict how they will affect the accuracy of the reconstructed shape. Our results for orthographic cameras show that the bas-relief ambiguity is significant even with many images, unless a large amount of rotation is present. Similar results for perspective cameras suggest that three or more frames and a large amount of rotation are required for metrically accurate reconstruction.

PDF ECCV Semantic Scholar

Cite

Text

Szeliski and Kang. "Shape Ambiguities in Structure from Motion." European Conference on Computer Vision, 1996. doi:10.1007/BFB0015580

Markdown

[Szeliski and Kang. "Shape Ambiguities in Structure from Motion." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/szeliski1996eccv-shape/) doi:10.1007/BFB0015580

BibTeX

@inproceedings{szeliski1996eccv-shape,
  title     = {{Shape Ambiguities in Structure from Motion}},
  author    = {Szeliski, Richard and Kang, Sing Bing},
  booktitle = {European Conference on Computer Vision},
  year      = {1996},
  pages     = {709-721},
  doi       = {10.1007/BFB0015580},
  url       = {https://mlanthology.org/eccv/1996/szeliski1996eccv-shape/}
}