A lightweight C++ library for recursive bilateral filtering [Yang, Qingxiong. "Recursive bilateral filtering". European Conference on Computer Vision, 2012].
C C++
Switch branches/tags
Nothing to show
Clone or download
Latest commit 1164edc May 17, 2017
Permalink
Failed to load latest commit information.
example Add CMake support May 17, 2017
include Add CMake support May 17, 2017
.gitattributes New start from here May 15, 2017
.gitignore Add CMake support May 17, 2017
LICENSE Create LICENSE May 15, 2017
README.md New start from here May 15, 2017
_config.yml New start from here May 15, 2017

README.md

Recursive bilateral filtering (developed by Qingxiong Yang) is pretty fast compared with most edge-preserving filtering methods

  • computational complexity is linear in both input size and dimensionality:
  • takes about 43 ms to process a one megapixel color image (i7 1.8GHz & 4GB mem)
  • about 18x faster than Fast high-dimensional filtering using the permutohedral lattice
  • about 86x faster than Gaussian kd-trees for fast high-dimensional filtering

Results


Original Image


OpenCV's BF (896ms)


RecursiveBF (18ms)


Gaussian Blur


Median Blur

For more details of the algorithm, please refer to the original paper

@inproceedings{yang2012recursive,
    title={Recursive bilateral filtering},
    author={Yang, Qingxiong},
    booktitle={European Conference on Computer Vision},
    pages={399--413},
    year={2012},
    organization={Springer}
}