Share Email Print

Proceedings Paper

Night colorize: fully convolutional colorization network for low-light images
Author(s): Lubin Xia; Li Li; Weiqi Jin; Su Qiu; Hongchang Cheng
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

An end-to-end network is proposed for low-light images natural colorization using a deep fully convolutional architecture. The network consists of a downsampling sub-network and an upsampling sub-network. The downsampling component extracts the high-level features of the input images, while the upsampling component transforms the high-level features to color. A skip connection is used to transmit low layer information to the deep layer so as to improve the colorization accuracy. Gamma correction and random noise augmentation are used to improve the network adaptability to low-light images. The trained model can naturally colorize low-light images without any reference image or artificial scribbles.

Paper Details

Date Published: 27 November 2019
PDF: 6 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113210T (27 November 2019); doi: 10.1117/12.2547902
Show Author Affiliations
Lubin Xia, Beijing Institute of Technology (China)
Li Li, Beijing Institute of Technology (China)
Weiqi Jin, Beijing Institute of Technology (China)
Su Qiu, Beijing Institute of Technology (China)
Hongchang Cheng, Science and Technology on Low-Light-Level Night Vision Lab. (China)

Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?