2518

Accurate multi-view reconstruction using robust binocular stereo and surface meshing

Derek Bradley, Tamy Boubekeur, Wolfgang Heidrich
University of British Columbia
IEEE Conference on Computer Vision and Pattern Recognition, 2008. CVPR 2008, p.1-8

@conference{bradley2008accurate,

   title={Accurate multi-view reconstruction using robust binocular stereo and surface meshing},

   author={Bradley, D. and Boubekeur, T. and Heidrich, W.},

   booktitle={Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on},

   pages={1–8},

   issn={1063-6919},

   year={2008},

   organization={IEEE}

}

Download Download (PDF)   View View   Source Source   

748

views

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.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: