ML Anthology

Multicore Bundle Adjustment

Changchang Wu, Sameer Agarwal, Brian Curless, Steven M. Seitz
CVPR 2011 pp. 3057-3064
doi:10.1109/CVPR.2011.5995552 /cvpr/2011/wu2011cvpr-multicore/

Abstract

We present the design and implementation of new inexact Newton type Bundle Adjustment algorithms that exploit hardware parallelism for efficiently solving large scale 3D scene reconstruction problems. We explore the use of multicore CPU as well as multicore GPUs for this purpose. We show that overcoming the severe memory and bandwidth limitations of current generation GPUs not only leads to more space efficient algorithms, but also to surprising savings in runtime. Our CPU based system is up to ten times and our GPU based system is up to thirty times faster than the current state of the art methods, while maintaining comparable convergence behavior. The code and additional results are available at http://grail.cs.washington.edu/projects/mcba.

CVPR Semantic Scholar

Cite

Text

Wu et al. "Multicore Bundle Adjustment." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995552

Markdown

[Wu et al. "Multicore Bundle Adjustment." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/wu2011cvpr-multicore/) doi:10.1109/CVPR.2011.5995552

BibTeX

@inproceedings{wu2011cvpr-multicore,
  title     = {{Multicore Bundle Adjustment}},
  author    = {Wu, Changchang and Agarwal, Sameer and Curless, Brian and Seitz, Steven M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {3057-3064},
  doi       = {10.1109/CVPR.2011.5995552},
  url       = {https://mlanthology.org/cvpr/2011/wu2011cvpr-multicore/}
}