Skip to content

A naïve implementation of the Fast Bilateral-Space Stereo method from the Fast Bilateral-Space Stereo for Synthetic Defocus paper by Jon Barron.

License

Notifications You must be signed in to change notification settings

H1Gdev/fast_bilateral_space_stereo

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Fast Bilateral-Space Stereo

A naïve implementation of the Fast Bilateral-Space Stereo paper by Jonathan T. Barron. [1] [2] [3]
The goal of this project was to get an intuition of this method. Therefore writing performant code was not a criteria.
Only the simplified bilateral grid method without the multiscale optimization is implemented.
The algorithm needs a stereo pair as input and will generate a disparity map.

More details about this implementation can be found at http://tvdz.be/2017/03/fast-bilateral-space-stereo/.

Dependencies

The following dependencies are needed.
The version numbers are the ones used during development.

  • OpenCV 3.2.0
    • (optional) opencv_contrib (if you want to use the domain transform filter to smoothen the disparity map)
  • Eigen 3.3.2
  • Ceres Solver 1.12.0
    • Glog 0.3.3
    • GFlags 2.2.0

The code was developed on a Windows machine with Visual Studio 2015.

References

[1] Barron, Jonathan T., et al. "Fast bilateral-space stereo for synthetic defocus." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015.

[2] Barron, Jonathan T., et al. "Fast bilateral-space stereo for synthetic defocus—Supplemental material." Proc. IEEE Conf. Comput. Vis. Pattern Recognit.(CVPR). 2015.

[3] Barron, Jonathan T., http://jonbarron.info/

About

A naïve implementation of the Fast Bilateral-Space Stereo method from the Fast Bilateral-Space Stereo for Synthetic Defocus paper by Jon Barron.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 86.3%
  • CMake 13.7%