Guys,
I have been following this project online and they have release the source code maybe be of use for people working on robots with vision.
Cheers,
Daniel Zimmer
*Dear Colleagues,
We are happy to announce the release of source-code for LSD-SLAM on github.
We also offer a number of example-videos including camera calibration & generated map, to get you started.
The link to the code, documentation and the datasets are available here:
http://vision.in.tum.de/lsdslam
We hope LSD-SLAM will be useful and spark interest and further research towards
direct visual SLAM methods. If you use our code or datasets please cite the related paper(s):
- LSD-SLAM: Large-Scale Direct Monocular SLAM; J. Engel, T. Schöps, D. Cremers; ECCV '14
PDF: https://vision.in.tum.de/_media/spezial/bib/engel14eccv.pdf - Semi-Dense Visual Odometry for AR on a Smartphone; T. Schöps, J. Engel, D. Cremers; ISMAR '14
PDF: http://vision.in.tum.de/_media/spezial/bib/schoeps14ismar.pdf - Semi-Dense Visual Odometry for a Monocular Camera; J. Engel, J. Sturm, D. Cremers; ICCV '13
PDF: http://vision.in.tum.de/_media/spezial/bib/engel2013iccv.pdf
The code is released under GPLv3, however we also offer closed-source (commercial) licensing models.
Best Regards,
Jakob Engel, Thomas Schöps, Daniel Cremers*