Skip to content

Poplar implementation of "Bundle Adjustment on a Graph Processor" (CVPR 2020)

License

Notifications You must be signed in to change notification settings

yiakwy-xpu-ml-framework-team/GC-OXFORD-CVPR2021-gbp-poplar

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Poplar Implementation of Bundle Adjustment using Gaussian Belief Propagation on Graphcore's IPU

Implementation of CVPR 2020 paper: Bundle Adjustment on a Graph Processor

Find the Poplar SDK documentation here. Code has been tested on Poplar SDK 1.2.

Find the corresponding python implementation here.

Running Bundle Adjustment

cd ba
make ba
./ba --bal_file ../sequences/fr1xyz.txt

For more options

./ba --help

Running SLAM

cd ba
make slam
./slam --bal_file ../sequences/fr2robot2.txt 

Citation

If you find our work useful in your research, please consider citing:

@InProceedings{OrtizCVPR2020,
author = {Ortiz, Joseph and Pupilli, Mark and Leutenegger, Stefan and Davison, Andrew J.},
title = {Bundle Adjustment on a Graph Processor},
booktitle = {{Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}},
year = {2020}
}

About

Poplar implementation of "Bundle Adjustment on a Graph Processor" (CVPR 2020)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 99.8%
  • Makefile 0.2%