@Article{HassanAhmedSial2020,
author="Hassan Ahmed Sial
and Ramon Baldrich
and Maria Vanrell",
title="Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects",
journal="Journal of the Optical Society of America A",
year="2020",
volume="37",
number="1",
pages="1--15",
abstract="Estimation of intrinsic images still remains a challenging task due to weaknesses of ground-truth datasets, which either are too small or present non-realistic issues. On the other hand, end-to-end deep learning architectures start to achieve interesting results that we believe could be improved if important physical hints were not ignored. In this work, we present a twofold framework: (a) a flexible generation of images overcoming some classical dataset problems such as larger size jointly with coherent lighting appearance; and (b) a flexible architecture tying physical properties through intrinsic losses. Our proposal is versatile, presents low computation time, and achieves state-of-the-art results.",
optnote="CIC; 600.140; 600.12; 600.118",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3311), last updated on Tue, 09 Feb 2021 10:58:53 +0100",
opturl="https://doi.org/10.1364/JOSAA.37.000001",
file=":http://refbase.cvc.uab.es/files/SBV2019.pdf:PDF"
}