File Exchange

image thumbnail

Sensor-Independent Illuminant Estimation Using Deep Learning

version 1.0.5 (327 MB) by Mahmoud Afifi
Sensor-Independent Illumination Estimation for DNN Models (BMVC 2019)

2 Downloads

Updated 23 Mar 2020

GitHub view license on GitHub

Implementation of our paper: Sensor-Independent Illumination Estimation for DNN Models, BMVC, 2019.

Learning a new canonical space in an unsupervised manner allows us to train a single deep model on multiple camera sensors in order to estimate scene illuminant captured by a new unseen sensor.

Paper: https://bmvc2019.org/wp-content/uploads/papers/0105-paper.pdf
Project page: http://cvil.eecs.yorku.ca/projects/public_html/siie/

Cite As

Mahmoud Afifi and Michael S. Brown. Sensor-Independent Illumination Estimation for DNN Models. In British Machine Vision Conference (BMVC), 2019

Comments and Ratings (0)

Updates

1.0.5

support Matlab 2019b or higher

1.0.4

updated summary

1.0.3

updated description

1.0.2

.

1.0.1

paper info is added

MATLAB Release Compatibility
Created with R2019b
Compatible with R2018b to any release
Platform Compatibility
Windows macOS Linux