TY  - JOUR
AU  - Hassan Ahmed Sial
AU  - Ramon Baldrich
AU  - Maria Vanrell
PY  - 2020//
TI  - Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects
T2  - JOSA A
JO  - Journal of the Optical Society of America A
SP  - 1
EP  - 15
VL  - 37
IS  - 1
N2  - 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.
UR  - https://doi.org/10.1364/JOSAA.37.000001
L1  - http://refbase.cvc.uab.es/files/SBV2019.pdf
N1  - CIC; 600.140; 600.12; 600.118
ID  - Hassan Ahmed Sial2020
ER  -