Skip to content
Go to file

Latest commit


Git stats


Failed to load latest commit information.
Latest commit message
Commit time

BASS: Boundary-Aware Superpixel Segmentation

Some results of the algorithm.

How do I get set up?

Clone the repo, go to code folder and compile as follows (you will need to remove an extra space created in link.txt):

$ cd code
$ mkdir build
$ cd build
$ cmake ..
$ sed -i 's/ --no-whole-archive/--no-whole-archive/g' CMakeFiles/bass.dir/link.txt 
$ make

How to make it work?

From the command line, run:

$ ./path_to_build/bass path_to_img_or_folder -s ns

where ns is the desired number of initial seeds for superpixels. The command will apply BASS in all the images in the folder. Results will be stored in path_to_img_or_folder/output, that needs to be previously created at this point (will be fixed in future updates).

For instance, from the root folder of this repo:

$ ./code/build/bass imgs/ -s 50

If you use this code, please cite the following paper:

BASS: Boundary-Aware Superpixel Segmentation
Antonio Rubio, Longlong Yu, Edgar Simo-Serra, Francesc Moreno-Noguer
International Conference on Pattern Recognition (ICPR), 2016

   author = {Antonio Rubio and Longlong Yu and Edgar Simo-Serra and Francesc Moreno-Noguer},
   title = {{BASS: Boundary-Aware Superpixel Segmentation}},
   booktitle = "Proceedings of the International Conference on Pattern Recognition (ICPR)",
   year = 2016,

Some tools for this code are extracted and/or modified from D.Stutz's work [1].

[1] D. Stutz, A. Hermans, B. Leibe.
Superpixel Segmentation using Depth Information.
Bachelor thesis, RWTH Aachen University, Aachen, Germany, 2014.


Code related to the paper "Boundary-Aware Superpixel Segmentation", sent to ICPR 2016.




No releases published


No packages published
You can’t perform that action at this time.