Next Article in Journal
A Systematic Review of the Multi-Resolution Modeling (MRM) for Integration of Live, Virtual, and Constructive Systems
Previous Article in Journal
Examining the Effects of eWOM, Trust Inclination, and Information Adoption on Purchase Intentions in an Accelerated Digital Marketing Context

Attentional Colorization Networks with Adaptive Group-Instance Normalization

by 1,2,*, 1,2, 1,2 and 1,2
Shanghai Film Academy, Shanghai University, Shanghai 200444, China
Shanghai Engineering Research Center for Motion Picture Special Effects, Shanghai 200444, China
Author to whom correspondence should be addressed.
Information 2020, 11(10), 479;
Received: 2 September 2020 / Revised: 29 September 2020 / Accepted: 9 October 2020 / Published: 13 October 2020
(This article belongs to the Section Artificial Intelligence)
We propose a novel end-to-end image colorization framework which integrates attention mechanism and a learnable adaptive normalization function. In contrast to previous colorization methods that directly generate the whole image, we believe that the color of the significant area determines the quality of the colorized image. The attention mechanism uses the attention map which is obtained by the auxiliary classifier to guide our framework to produce more subtle content and visually pleasing color in salient visual regions. Furthermore, we apply Adaptive Group Instance Normalization (AGIN) function to promote our framework to generate vivid colorized images flexibly, under the circumstance that we consider colorization as a particular style transfer task. Experiments show that our model is superior to previous the state-of-the-art models in coloring foreground objects. View Full-Text
Keywords: colorization; attention mechanism; normalization colorization; attention mechanism; normalization
Show Figures

Figure 1

MDPI and ACS Style

Gao, Y.; Ding, Y.; Wang, F.; Liang, H. Attentional Colorization Networks with Adaptive Group-Instance Normalization. Information 2020, 11, 479.

AMA Style

Gao Y, Ding Y, Wang F, Liang H. Attentional Colorization Networks with Adaptive Group-Instance Normalization. Information. 2020; 11(10):479.

Chicago/Turabian Style

Gao, Yuzhen, Youdong Ding, Fei Wang, and Huan Liang. 2020. "Attentional Colorization Networks with Adaptive Group-Instance Normalization" Information 11, no. 10: 479.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop