Sorry, you need to enable JavaScript to visit this website.

NEAR INFRARED IMAGERY COLORIZATION

Citation Author(s):
Patricia L. Suarez,Angel D. Sappa,Boris Vintimilla,Riad I. Hammoud
Submitted by:
Patricia Suarez
Last updated:
4 October 2018 - 7:21pm
Document Type:
Poster
Document Year:
2018
Event:
Presenters Name:
Patricia L. Suarez
Paper Code:
ICIP18001

Abstract 

Abstract: 

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 multiple loss 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.

up
0 users have voted:

Comments

ESPOL POLYTHECNIC GUAYAQUIL-ECUADOR

Dataset Files

NEAR INFRARED IMAGERY COLORIZATION.pdf

(138)