Probabilistic Labeling Cost for High-Accuracy Multi-View Reconstruction

Ilya Kostrikov, Esther Horbert, Bastian Leibe

CVPR 2014

doi:10.1109/CVPR.2014.199 /cvpr/2014/kostrikov2014cvpr-probabilistic/

Abstract

In this paper, we propose a novel labeling cost for multi- view reconstruction. Existing approaches use data terms with specific weaknesses that are vulnerable to common challenges, such as low-textured regions or specularities. Our new probabilistic method implicitly discards outliers and can be shown to become more exact the closer we get to the true object surface. Our approach achieves top results among all published methods on the Middlebury DINO SPARSE dataset and also delivers accurate results on several other datasets with widely varying challenges, for which it works in unchanged form.

PDF CVPR Semantic Scholar

Cite

Text

Kostrikov et al. "Probabilistic Labeling Cost for High-Accuracy Multi-View Reconstruction." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.199

Markdown

[Kostrikov et al. "Probabilistic Labeling Cost for High-Accuracy Multi-View Reconstruction." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/kostrikov2014cvpr-probabilistic/) doi:10.1109/CVPR.2014.199

BibTeX

@inproceedings{kostrikov2014cvpr-probabilistic,
  title     = {{Probabilistic Labeling Cost for High-Accuracy Multi-View Reconstruction}},
  author    = {Kostrikov, Ilya and Horbert, Esther and Leibe, Bastian},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.199},
  url       = {https://mlanthology.org/cvpr/2014/kostrikov2014cvpr-probabilistic/}
}