%0 Conference Proceedings
%T Names and Shades of Color for Intrinsic Image Estimation
%A Marc Serra
%A Olivier Penacchio
%A Robert Benavente
%A Maria Vanrell
%B 25th IEEE Conference on Computer Vision and Pattern Recognition
%D 2012
%I IEEE Xplore
%@ 1063-6919
%@ 978-1-4673-1226-4
%F Marc Serra2012
%O CIC
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2026), last updated on Fri, 14 Feb 2014 11:24:06 +0100
%X In the last years, intrinsic image decomposition has gained attention. Most of the state-of-the-art methods are based on the assumption that reflectance changes come along with strong image edges. Recently, user intervention in the recovery problem has proved to be a remarkable source of improvement. In this paper, we propose a novel approach that aims to overcome the shortcomings of pure edge-based methods by introducing strong surface descriptors, such as the color-name descriptor which introduces high-level considerations resembling top-down intervention. We also use a second surface descriptor, termed color-shade, which allows us to include physical considerations derived from the image formation model capturing gradual color surface variations. Both color cues are combined by means of a Markov Random Field. The method is quantitatively tested on the MIT ground truth dataset using different error metrics, achieving state-of-the-art performance.
%U http://ieeexplore.ieee.org/xpl/articleDetails.jsp? arnumber=6247686
%U http://refbase.cvc.uab.es/files/SPB2012a.pdf
%U http://dx.doi.org/10.1109/CVPR.2012.6247686
%P 278-285