ML Anthology

Multi-Planar Fitting in an Indoor ManhattanWorld

Seongdo Kim, Roberto Manduchi
WACV 2017 pp. 11-19
doi:10.1109/WACV.2017.9 /wacv/2017/kim2017wacv-multi/

Abstract

We present an algorithm that finds planar structures in a Manhattan world from two pictures taken from different viewpoints with unknown baseline. The Manhattan world assumption constrains the homographies induced by the visible planes on the image pair, thus enabling robust reconstruction. We extend the T-linkage algorithm for multistructure discovery to account for constrained homographies, and introduce algorithms for sample point selection and orientation-preserving cluster merging. Results are presented on three indoor data set, showing the benefit of the proposed constraints and algorithms.

PDF WACV Semantic Scholar

Cite

Text

Kim and Manduchi. "Multi-Planar Fitting in an Indoor ManhattanWorld." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017. doi:10.1109/WACV.2017.9

Markdown

[Kim and Manduchi. "Multi-Planar Fitting in an Indoor ManhattanWorld." IEEE/CVF Winter Conference on Applications of Computer Vision, 2017.](https://mlanthology.org/wacv/2017/kim2017wacv-multi/) doi:10.1109/WACV.2017.9

BibTeX

@inproceedings{kim2017wacv-multi,
  title     = {{Multi-Planar Fitting in an Indoor ManhattanWorld}},
  author    = {Kim, Seongdo and Manduchi, Roberto},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2017},
  pages     = {11-19},
  doi       = {10.1109/WACV.2017.9},
  url       = {https://mlanthology.org/wacv/2017/kim2017wacv-multi/}
}