English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Color constancy is our ability to perceive constant colors across varyingilluminations. Here, we trained deep neural networks to be color constant andevaluated their performance with varying cues. Inputs to the networks consistedof the cone excitations in 3D-rendered images of 2115 different 3D-shapes, withspectral reflectances of 1600 different Munsell chips, illuminated under 278different natural illuminations. The models were trained to classify thereflectance of the objects. One network, Deep65, was trained under a fixeddaylight D65 illumination, while DeepCC was trained under varyingilluminations. Testing was done with 4 new illuminations with equally spacedCIEL*a*b* chromaticities, 2 along the daylight locus and 2 orthogonal to it. Wefound a high degree of color constancy for DeepCC, and constancy was higheralong the daylight locus. When gradually removing cues from the scene,constancy decreased. High levels of color constancy were achieved withdifferent DNN architectures. Both ResNets and classical ConvNets of varyingdegrees of complexity performed well. However, DeepCC, a convolutional network,represented colors along the 3 color dimensions of human color vision, whileResNets showed a more complex representation.

Deep Neural Models for color discrimination and color constancy