Light Field toolbox - Recolouring step
This code is mostly meant to correct colour inconsistencies in Light Field datasets taken using plenoptic cameras . This will allow you to propagate the colours from the centre of a Light Field to all the images, which will ensure you get consistent sub-aperture images accross the whole set.
If you use or adapt any part of this code in your work, please remember to cite the appropriate paper .
- Authors : Pierre Matysiak (email@example.com), Mairéad Grogan (firstname.lastname@example.org)
- Copyright : (c) 2018 V-Sense
- License : GPL v3+, see GPLv3.txt
For additional details and visual results, see our webpage.
The proper order in which to use these tools is : RAW data demultiplexing --> Recolouring --> Denoising.
For simplicity's sake, we made it so that you only have to use the one file, everything else is done automatically :
- put any number of datasets in the folder called "data"
- at the beginning of the file "recolour_centre_neighbour.m", add/replace the paths to your datasets, assuming that the root folder is ".../data/"
- launch the code by calling "recolour_centre_neighbour.m" ; no arguments are necessary.
Please note that the recolouring code uses OpenMP, please make sure you have the proper dependancies installed and that your compiler supports it.
 P. Matysiak, M. Grogan, M. Le Pendu, M. Alain and A. Smolic, "A Pipeline for Lenslet Light Field Quality Enhancement", International Conference on Image Processing (ICIP) 2018.
 M. Grogan and R. Dahyot, “Robust registration of gaussian mixtures for colour transfer”, ArXiv e-prints (May 2017). arXiv:cs.CV/1705.06091.
 Y. Hu, R. Song, and Y. Li, “Efficient coarse-to-fine patchmatch for large displacement optical flow”, in Proc. CVPR, 2016.