Back to articles
Articles
Volume: 1 | Article ID: art00032
Image
Light Direction and Color Estimation from Single Image with Deep Regression
  DOI :  10.2352/issn.2694-118X.2020.LIM-25  Published OnlineSeptember 2020
Abstract

We present a method to estimate the direction and color of a 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 SID dataset; (b) we define a deep architecture trained on the mentioned dataset to estimate direction and color of the scene light source. Apart from showing a 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 a good performance when it is applied to real scenes.

Subject Areas :
Views 21
Downloads 4
 articleview.views 21
 articleview.downloads 4
  Cite this article 

Hassan A. Sial, Ramon Baldrich, Maria Vanrell, Dimitris Samaras, "Light Direction and Color Estimation from Single Image with Deep Regressionin Proc. IS&T London Imaging Meeting 2020: Future Colour Imaging,  2020,  pp 139 - 143,  https://doi.org/10.2352/issn.2694-118X.2020.LIM-25

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
75011771
London Imaging Meeting
2694-118X
2694-118x
Society for Imaging Science and Technology