Occluding Contours for Multi-View Stereo

Qi Shan, Brian Curless, Yasutaka Furukawa, Carlos Hernandez, Steven M. Seitz

CVPR 2014

doi:10.1109/CVPR.2014.511 /cvpr/2014/shan2014cvpr-occluding/

Abstract

This paper leverages occluding contours (aka "internal silhouettes") to improve the performance of multi-view stereo methods. The contributions are 1) a new technique to identify free-space regions arising from occluding contours, and 2) a new approach for incorporating the resulting free-space constraints into Poisson surface reconstruction. The proposed approach outperforms state of the art MVS techniques for challenging Internet datasets, yielding dramatic quality improvements both around object contours and in surface detail.

PDF CVPR Semantic Scholar

Cite

Text

Shan et al. "Occluding Contours for Multi-View Stereo." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.511

Markdown

[Shan et al. "Occluding Contours for Multi-View Stereo." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/shan2014cvpr-occluding/) doi:10.1109/CVPR.2014.511

BibTeX

@inproceedings{shan2014cvpr-occluding,
  title     = {{Occluding Contours for Multi-View Stereo}},
  author    = {Shan, Qi and Curless, Brian and Furukawa, Yasutaka and Hernandez, Carlos and Seitz, Steven M.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.511},
  url       = {https://mlanthology.org/cvpr/2014/shan2014cvpr-occluding/}
}