ML Anthology

Combined Depth and Outlier Estimation in Multi-View Stereo

Christoph Strecha, Rik Fransens, Luc Van Gool
CVPR 2006 pp. 2394-2401
doi:10.1109/CVPR.2006.78 /cvpr/2006/strecha2006cvpr-combined/

Abstract

In this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes: (i) an inlier process, which generates the pixels which are visible from the reference camera and which obey the constant brightness assumption, and (ii) an outlier process which generates all other pixels. Depth and visibility are jointly modelled as a hiddenMarkov Random Field, and the spatial correlations of both are explicitly accounted for. Inference is made tractable by an EM-algorithm, which alternates between estimation of visibility and depth, and optimisation of model parameters. We describe and compare two implementations of the E-step of the algorithm, which correspond to the Mean Field and Bethe approximations of the free energy. The approach is validated by experiments on challenging real-world scenes, of which two are contaminated by independently moving objects.

PDF CVPR Semantic Scholar

Cite

Text

Strecha et al. "Combined Depth and Outlier Estimation in Multi-View Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.78

Markdown

[Strecha et al. "Combined Depth and Outlier Estimation in Multi-View Stereo." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/strecha2006cvpr-combined/) doi:10.1109/CVPR.2006.78

BibTeX

@inproceedings{strecha2006cvpr-combined,
  title     = {{Combined Depth and Outlier Estimation in Multi-View Stereo}},
  author    = {Strecha, Christoph and Fransens, Rik and Van Gool, Luc},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {2394-2401},
  doi       = {10.1109/CVPR.2006.78},
  url       = {https://mlanthology.org/cvpr/2006/strecha2006cvpr-combined/}
}