%0 Conference Proceedings
%T Light Direction and Color Estimation from Single Image with Deep Regression
%A Hassan Ahmed Sial
%A Ramon Baldrich
%A Maria Vanrell
%A Dimitris Samaras
%B London Imaging Conference
%D 2020
%F Hassan Ahmed Sial2020
%O CIC; 600.118; 600.140;
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3460), last updated on Tue, 09 Feb 2021 10:19:13 +0100
%X We present a method to estimate the direction and color of the scene light source from a single image. Our method is based on two main ideas: (a) we use a new synthetic dataset with strong shadow effects with similar constraints to the SID dataset; (b) we define a deep architecture trained on the mentioned dataset to estimate the direction and color of the scene light source. Apart from showing good performance on synthetic images, we additionally propose a preliminary procedure to obtain light positions of the Multi-Illumination dataset, and, in this way, we also prove that our trained model achieves good performance when it is applied to real scenes.
%U http://refbase.cvc.uab.es/files/SBV2020.pdf