Accurate Multi-View Reconstruction Using Robust Binocular Stereo and Surface Meshing

Abstract

This paper presents a new algorithm for multi-view reconstruction that demonstrates both accuracy and efficiency. Our method is based on robust binocular stereo matching, followed by adaptive point-based filtering of the merged point clouds, and efficient, high-quality mesh generation. All aspects of our method are designed to be highly scalable with the number of views. Our technique produces the most accurate results among current algorithms for a sparse number of viewpoints according to the Middlebury datasets. Additionally, we prove to be the most efficient method among non-GPU algorithms for the same datasets. Finally, our scaled-window matching technique also excels at reconstructing deformable objects with high-curvature surfaces, which we demonstrate with a number of examples.

Cite

Text

Bradley et al. "Accurate Multi-View Reconstruction Using Robust Binocular Stereo and Surface Meshing." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587792

Markdown

[Bradley et al. "Accurate Multi-View Reconstruction Using Robust Binocular Stereo and Surface Meshing." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/bradley2008cvpr-accurate/) doi:10.1109/CVPR.2008.4587792

BibTeX

@inproceedings{bradley2008cvpr-accurate,
  title     = {{Accurate Multi-View Reconstruction Using Robust Binocular Stereo and Surface Meshing}},
  author    = {Bradley, Derek and Boubekeur, Tamy and Heidrich, Wolfgang},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2008},
  doi       = {10.1109/CVPR.2008.4587792},
  url       = {https://mlanthology.org/cvpr/2008/bradley2008cvpr-accurate/}
}