TY  - CONF
AU  - Patricia Suarez
AU  - Angel Sappa
AU  - Boris X. Vintimilla
AU  - Riad I. Hammoud
A2  - ICIP
PY  - 2018//
TI  - Near InfraRed Imagery Colorization
BT  - 25th International Conference on Image Processing
SP  - 2237
EP  - 2241
KW  - Convolutional Neural Networks (CNN)
KW  - Generative Adversarial Network (GAN)
KW  - Infrared Imagery colorization
N2  - This paper proposes a stacked conditional Generative Adversarial Network-based method for Near InfraRed (NIR) imagery colorization. We propose a variant architecture of Generative Adversarial Network (GAN) that uses multipleloss functions over a conditional probabilistic generative model. We show that this new architecture/loss-function yields better generalization and representation of the generated colored IR images. The proposed approach is evaluated on a large test dataset and compared to recent state of the art methods using standard metrics.
L1  - http://refbase.cvc.uab.es/files/SSV2018b.pdf
UR  - http://dx.doi.org/10.1109/ICIP.2018.8451413
N1  - MSIAU; 600.086; 600.130; 600.122
ID  - Patricia Suarez2018
ER  -