TY  - CONF
AU  - Marc Serra
AU  - Olivier Penacchio
AU  - Robert Benavente
AU  - Maria Vanrell
A2  - CVPR
PY  - 2012//
TI  - Names and Shades of Color for Intrinsic Image Estimation
BT  - 25th IEEE Conference on Computer Vision and Pattern Recognition
SP  - 278
EP  - 285
PB  - IEEE Xplore
N2  - 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.
SN  - 1063-6919
SN  - 978-1-4673-1226-4
UR  - http://ieeexplore.ieee.org/xpl/articleDetails.jsp? arnumber=6247686
L1  - http://refbase.cvc.uab.es/files/SPB2012a.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2012.6247686
N1  - CIC
ID  - Marc Serra2012
ER  -