Color by Correlation: A Simple, Unifying Framework for Color Constancy

By Graham David Finlayson, Steven D. Hordley, P. Hubel. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001

626 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition, Social Psychology

View Paper: https://www.semanticscholar.org/paper/182ef3ebdbe7cebcef09f99c76a56bab2a4c0798

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

In Social Psychology

Citations in the corpus

Using Color Compatibility for Assessing Image Realism (2007, background): “[7], in which they determine the illumination based on nearest-neighbor matching to a set of illumination palettes.”
A comparison of computational color constancy algorithms. I: Methodology and experiments with synthesized data (2002, methodology): “In the case of the Color by Correlation methods, this is simply due to the discretization of the input.”
What is the space of camera response functions? (2003, methodology): “Examples of algorithms that explicitly use scene radiance measurements are color constancy [7, 13], construction of linear high dynamic range images [17, 4, 16], photometric stereo [2, 18, 20], shape from shading [12], estimation of reflectance and illumination from shape and brightness [14], recove”
Modeling the space of camera response functions (2004, methodology): “Examples of algorithms that explicitly use scene radiance measurements are color constancy [10], [19], construction of linear high-dynamic range images [3], [21], [26], [6], [22], photometric stereo [2], [28], [31], shape from shading [17], [28], [33], estimation of reflectance and illumination from”
Ieee Transactions on Pattern Analysis and Machine Intelligence Shape, Illumination, and Reflectance from Shading (neutral): “More recent work uses contemporary probabilistic tools, such as modeling the correlation between colors in a scene [19], or performing inference over priors on reflectance and illumination [20].”
Edge-Based Color Constancy (2007, neutral): “A framework which June 14, 2007 DRAFT inria-00548686, version 1 -20 Dec 2010 unifies multiple color constancy algorithms together is presented by Finlayson and Hordley [9].”
A comparison of computational color constancy Algorithms. II. Experiments with image data (2002, positive): “Recently, Finlayson et el. introduced Color by Correlation [ 29-31 ] as an improvement on the Color in”
Color Constancy, Intrinsic Images, and Shape Estimation (2012, methodology): “Retinex ignores shape and attempts to recover illumination and reflectance in isolation, assumptions shared by nearly all subsequent work in color constancy [6–11].”
On the removal of shadows from images (2006, background): “Estimating and accounting for the colour of the prevailing scene illumination is a related problem which has received much attention [11], [12], [13], [14], [15], [16], [17], [18], [19], [20].”