PT Journal
AU Hassan Ahmed Sial
   Ramon Baldrich
   Maria Vanrell
TI Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects
SO Journal of the Optical Society of America A
JI JOSA A
PY 2020
BP 1
EP 15
VL 37
IS 1
AB 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.
ER