ML Anthology

Robust Global Translations with 1DSfM

Kyle Wilson, Noah Snavely
ECCV 2014 pp. 61-75
doi:10.1007/978-3-319-10578-9_5 /eccv/2014/wilson2014eccv-robust/

Abstract

We present a simple, effective method for solving structure from motion problems by averaging epipolar geometries. Based on recent successes in solving for global camera rotations using averaging schemes, we focus on the problem of solving for 3D camera translations given a network of noisy pairwise camera translation directions (or 3D point observations). To do this well, we have two main insights. First, we propose a method for removing outliers from problem instances by solving simpler low-dimensional subproblems, which we refer to as 1DSfM problems. Second, we present a simple, principled averaging scheme. We demonstrate this new method in the wild on Internet photo collections.

PDF ECCV Semantic Scholar

Cite

Text

Wilson and Snavely. "Robust Global Translations with 1DSfM." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10578-9_5

Markdown

[Wilson and Snavely. "Robust Global Translations with 1DSfM." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/wilson2014eccv-robust/) doi:10.1007/978-3-319-10578-9_5

BibTeX

@inproceedings{wilson2014eccv-robust,
  title     = {{Robust Global Translations with 1DSfM}},
  author    = {Wilson, Kyle and Snavely, Noah},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {61-75},
  doi       = {10.1007/978-3-319-10578-9_5},
  url       = {https://mlanthology.org/eccv/2014/wilson2014eccv-robust/}
}