A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms

Abstract

This paper presents a quantitative comparison of several multi-view stereo reconstruction algorithms. Until now, the lack of suitable calibrated multi-view image datasets with known ground truth (3D shape models) has prevented such direct comparisons. In this paper, we first survey multi-view stereo algorithms and compare them qualitatively using a taxonomy that differentiates their key properties. We then describe our process for acquiring and calibrating multiview image datasets with high-accuracy ground truth and introduce our evaluation methodology. Finally, we present the results of our quantitative comparison of state-of-the-art multi-view stereo reconstruction algorithms on six benchmark datasets. The datasets, evaluation details, and instructions for submitting new models are available online at http://vision.middlebury.edu/mview.

Cite

Text

Seitz et al. "A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006. doi:10.1109/CVPR.2006.19

Markdown

[Seitz et al. "A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2006.](https://mlanthology.org/cvpr/2006/seitz2006cvpr-comparison/) doi:10.1109/CVPR.2006.19

BibTeX

@inproceedings{seitz2006cvpr-comparison,
  title     = {{A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms}},
  author    = {Seitz, Steven M. and Curless, Brian and Diebel, James and Scharstein, Daniel and Szeliski, Richard},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2006},
  pages     = {519-528},
  doi       = {10.1109/CVPR.2006.19},
  url       = {https://mlanthology.org/cvpr/2006/seitz2006cvpr-comparison/}
}