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...
Saved in:
Published in | 2019 IEEE International Conference on Image Processing (ICIP) pp. 2811 - 2815 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.09.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |