Single and Multiple Illuminant Estimation Using Convolutional Neural Networks

Abstract

Abstract-In this paper we present a method for the estimation of the color of the illuminant in RAW images. The method includes a Convolutional Neural Network that has been specially designed to produce multiple local estimates. A multiple illuminant detector determines whether or not the local outputs of the network must be aggregated into a single estimate. We evaluated our method on standard datasets with single and multiple illuminants, obtaining lower estimation errors with respect to those obtained by other general purpose methods in the state of the art.

Color Cerberus

“…On the other hand, more principled analysis of local illumination histograms as performed in [1] has clear advantages. One can easily see the connections of this approach to both classical gamut estimation in color vision, and a popular PointNet architecture for 3d point cloud processing.…”

“…We experimented with them during the competition, although these nets were slower to train and showed themselves worse on early validations. However, local estimator from [1] shows great quality with less parameter tuning 8.…”

“…That work was superseded by [1], with a slightly deeper net as a local illuminant estimator. It also has a sophisticated averaging procedure.…”

Improving CNN-Based Texture Classification by Color Balancing

“…Gamut mapping assumes that for a given illuminant, one observes only a limited gamut of colors [26]. Learning-based methods also exist, such as Bayesian [27], CART-based [28], and CNN-based [29,30] approaches, among others.…”

“…light-raw: it performs the correction of the illuminant color, similarly to what is done by color constancy algorithms [5,30,48] and chromatic adaptation transforms [49,50]. The output color representation is still device-dependent, but with the discount of the effect of the illuminant color; 3.…”