Colour Constancy

About

This website presents work about Color Constancy and holds the additional material to the CVPR 2008 paper Bayesian Color Constancy Revisited (conference poster). The main work for the paper was done during an internship of the first author at the Vision Group at Microsoft Research Cambridge. You can download the dataset and the code used for the experiments in the paper. In case of questions please write an email to the contact person.

Color constancy is the tendency to perceive surface color consistently, despite variations in ambient illumination. In this work we revisted the work presented in Bayesian Color Constancy with Non-Gaussian Models and investigated the use of more precice reflectance priors for Color Constancy. We collected a new dataset for Color Constancy consisting of different scenes, both indoor and outdoor taken under different illuminations. In each scene a Gretag MacBeth Color Checker Chart was placed such that it was illuminated by the main scene illuminant and thus its color could be retrieved. The code used for the experiments in the paper is also available.

Dataset

Important: Different versions of this dataset exists. In case you are interested in a linear re-processing of the images I strongly recommend that you visit http://colour.cmp.uea.ac.uk/datasets/reprocessed-gehler.html and use the data made available there. The data you find there should be the one you want to work on! This website will be updated soon for a more complete description of the processing and different versions. Until then please visit the site mentioned above and use this site only if you are interested in the original RAW files.

What follows is the original description, this will be updated! Some example scenes of the dataset are shown below. The data is available in Canon RAW format free of any correction. For the experiment we use the Canon Digital Photo Professional Tool to convert the RAW images to TIFF format using the AutoWhitebalance setting of the camera. We also corrected for chromatic abberation in this step. The result was downsampled to 20% of the original size. You can download the RAW images split in the archives

(about 1000MB each (!)). Alternatively you can download the (600MB) which comes with the extracted color of the grey patches of the MacBeth Color Checker chart in r/g chromaticities. In both cases you may want to download the within the images to mask them in any experiments (file format explained in a readme file included in the archive). An accompanying file (outdoor.txt) separates the images in indoor and outdoor scenes.
In this file you will find more information about how the ground truth color values have been generated together with the use scripts to replicate them.

Extensions of the Dataset

This dataset has been re-processed by other researchers. To facilitate a fair comparison between differrent methods I recommend that you use the data provided here:

There are two other version of the dataset, but please refer to the link above for the most up-to-date version. This website will be updated soon for more complete information.


Example image from Color Checker Database Example image from Color Checker Database structureddsadsd feature
Example image from Color Checker Database Example image from Color Checker Database Example image from Color Checker Database
Example image from Color Checker Database Example image from Color Checker Database Example image from Color Checker Database

Code

The code is available as Matlab source code, some functions are written as MEX files which need to be compiled first. Most functions should have an help, so try "help < functionname >" for an explanation. Try the function "sample_run.m" for an example run of the Greyworld and Bayesian algorithm. We want to emphasize that the code is research code and thus only of "prototype" quality. For any questions about the code please write an email to Peter Gehler. You can download the code here.
The Greyworld algorithm is based on and almost identical in most parts with the code published by Joost van de Weijer at his color research website.

Publications

Bayesian Color Constancy Revisited - Peter V. Gehler, Carsten Rother, Andrew Blake, Toby Sharp and Tom Minka, CVPR 2008, Bibtex Entry

Contact

Contact person Peter Gehler.