Multi-Illuminant Estimation With Conditional Random Fields
- 18 October 2013
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (1), 83-96
- https://doi.org/10.1109/tip.2013.2286327
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 data set of two-dominant-illuminant 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 data sets. Experimental results show that our framework clearly outperforms single illuminant estimators as well as a recently proposed multi-illuminant estimation approach.Keywords
This publication has 37 references indexed in Scilit:
- Light mixture estimation for spatially varying white balanceACM Transactions on Graphics, 2008
- Color constancy from physical principlesPattern Recognition Letters, 2003
- A comparison of computational color constancy algorithms. I: Methodology and experiments with synthesized dataIEEE Transactions on Image Processing, 2002
- A comparison of computational color constancy Algorithms. II. Experiments with image dataIEEE Transactions on Image Processing, 2002
- A data set for color researchColor Research & Application, 2002
- Bayesian color constancyJournal of the Optical Society of America A, 1997
- Color Constancy for Scenes with Varying IlluminationComputer Vision and Image Understanding, 1997
- Method for computing the scene-illuminant chromaticity from specular highlightsJournal of the Optical Society of America A, 1986
- Using color to separate reflection componentsColor Research & Application, 1985
- The Retinex Theory of Color VisionScientific American, 1977