Colour in Context
Research group
Computer Vision Center

Multi-Illuminant Estimation with Conditional Random Fields

IEEE Transactions on Image Processing, Volume 23, Number 1, page 83--95 - jan 2014
Download the publication : TIP_2014.pdf [6.7Mo]  
Most existing color constancy algorithms assume uniform illumination. However, in real-world scenes, this is not often the case. Thus, we propose a novel framework for estimating the colors of multiple illuminants and their spatial distribution in the scene. We formulate this problem as an energy minimization task within a Conditional Random Field over a set of local illuminant estimates. In order to quantitatively evaluate the proposed method, we created a novel dataset of twodominant- illuminants images comprised of laboratory, indoor and outdoor scenes. Unlike prior work, our database includes accurate pixel-wise ground truth illuminant information. The performance of our method is evaluated on multiple datasets. Experimental results show that our framework clearly outperforms single illuminant estimators, as well as a recently proposed multi-illuminant estimation approach.

Images and movies

 

BibTex references

@Article\{BRV2014,
  author       = "Shida Beigpour and Christian Riess and Joost van de Weijer and Elli Angelopoulou",
  title        = "Multi-Illuminant Estimation with Conditional Random Fields",
  journal      = "IEEE Transactions on Image Processing",
  number       = "1",
  volume       = "23",
  pages        = "83--95",
  month        = "jan",
  year         = "2014",
  abstract     = "Most existing color constancy algorithms assume
uniform illumination. However, in real-world scenes, this is
not often the case. Thus, we propose a novel framework for
estimating the colors of multiple illuminants and their spatial
distribution in the scene. We formulate this problem as an
energy minimization task within a Conditional Random Field
over a set of local illuminant estimates. In order to quantitatively
evaluate the proposed method, we created a novel dataset of twodominant-
illuminants images comprised of laboratory, indoor
and outdoor scenes. Unlike prior work, our database includes
accurate pixel-wise ground truth illuminant information. The
performance of our method is evaluated on multiple datasets.
Experimental results show that our framework clearly outperforms
single illuminant estimators, as well as a recently proposed
multi-illuminant estimation approach.",
  url          = "http://www.cat.uab.cat/Public/Publications/2014/BRV2014"
}

Other publications in the database

 © 2008 Colour in context Group | Computer Vision Center. All rights reserved | Contact webmaster |  Last updated: Monday 11 May 2009     eXTReMe Tracker