ML Anthology

Multiview Specular Stereo Reconstruction of Large Mirror Surfaces

Jonathan Balzer, Sebastian Höfer, Jürgen Beyerer
CVPR 2011 pp. 2537-2544
doi:10.1109/CVPR.2011.5995346 /cvpr/2011/balzer2011cvpr-multiview/

Abstract

In deflectometry, the shape of mirror objects is recovered from distorted images of a calibrated scene. While remarkably high accuracies are achievable, state-of-the-art methods suffer from two distinct weaknesses: First, for mainly constructive reasons, these can only capture a few square centimeters of surface area at once. Second, reconstructions are ambiguous i.e. infinitely many surfaces lead to the same visual impression. We resolve both of these problems by introducing the first multiview specular stereo approach, which jointly evaluates a series of overlapping deflectometric images. Two publicly available benchmarks accompany this paper, enabling us to numerically demonstrate viability and practicability of our approach. © 2011 IEEE.

CVPR Semantic Scholar

Cite

Text

Balzer et al. "Multiview Specular Stereo Reconstruction of Large Mirror Surfaces." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995346

Markdown

[Balzer et al. "Multiview Specular Stereo Reconstruction of Large Mirror Surfaces." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/balzer2011cvpr-multiview/) doi:10.1109/CVPR.2011.5995346

BibTeX

@inproceedings{balzer2011cvpr-multiview,
  title     = {{Multiview Specular Stereo Reconstruction of Large Mirror Surfaces}},
  author    = {Balzer, Jonathan and Höfer, Sebastian and Beyerer, Jürgen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2537-2544},
  doi       = {10.1109/CVPR.2011.5995346},
  url       = {https://mlanthology.org/cvpr/2011/balzer2011cvpr-multiview/}
}