Low-Lightgan: Low-Light Enhancement Via Advanced Generative Adversarial Network With Task-Driven Training

We propose a low-light enhancement method using an advanced generative adversarial network (GAN) and a task-driven training set. Unlike traditional training sets that only synthesize global illumination, we apply local illumination to make the training images. Furthermore, we enhance traditional GAN...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE International Conference on Image Processing (ICIP) pp. 2811 - 2815
Main Authors Kim, Guisik, Kwon, Dokyeong, Kwon, Junseok
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2019
Subjects
Brightness
Gallium nitride
GANs
Generative adversarial networks
Image color analysis
Lighting
Low-light enhancement
spectral normalization
Task analysis
task-driven training set
Training
Online AccessGet full text

Cover

More Information
Summary:We propose a low-light enhancement method using an advanced generative adversarial network (GAN) and a task-driven training set. Unlike traditional training sets that only synthesize global illumination, we apply local illumination to make the training images. Furthermore, we enhance traditional GANs with spectral normalization and advanced loss functions, making training stable and leading to accurate results. Experimental results show that our method outperforms state-of-the art methods qualitatively and quantitatively and alleviates saturation problems in bright areas, which typically occur after traditional low-light enhancements.
ISSN:2381-8549
DOI:10.1109/ICIP.2019.8803328