Example-based colourization via dense encoding pyramids
We propose a novel deep example-based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large-scale data and then predicts...
Saved in:
Main Authors: | , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7837 https://ink.library.smu.edu.sg/context/sis_research/article/8840/viewcontent/example_based.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8840 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-88402023-06-15T09:14:23Z Example-based colourization via dense encoding pyramids XIAO, Chufeng HAN, Chu ZHANG, Zhuming QIN, Jing WONG, Tien-Tsin HAN, Guoqiang HE, Shengfeng We propose a novel deep example-based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large-scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi-scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder-encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local-global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state-of-the-art colourization methods. Experimental results show that our network is able to generate colourful, semantically correct and visually pleasant colour images. In addition, unlike fully automatic colourization that produces fixed colour images, the reference image of our network is flexible; both natural images and simple colour palettes can be used to guide the colourization. 2020-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7837 info:doi/10.1111/cgf.13659 https://ink.library.smu.edu.sg/context/sis_research/article/8840/viewcontent/example_based.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University image and video processing image processing Information Security |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
image and video processing image processing Information Security |
spellingShingle |
image and video processing image processing Information Security XIAO, Chufeng HAN, Chu ZHANG, Zhuming QIN, Jing WONG, Tien-Tsin HAN, Guoqiang HE, Shengfeng Example-based colourization via dense encoding pyramids |
description |
We propose a novel deep example-based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large-scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi-scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder-encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local-global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state-of-the-art colourization methods. Experimental results show that our network is able to generate colourful, semantically correct and visually pleasant colour images. In addition, unlike fully automatic colourization that produces fixed colour images, the reference image of our network is flexible; both natural images and simple colour palettes can be used to guide the colourization. |
format |
text |
author |
XIAO, Chufeng HAN, Chu ZHANG, Zhuming QIN, Jing WONG, Tien-Tsin HAN, Guoqiang HE, Shengfeng |
author_facet |
XIAO, Chufeng HAN, Chu ZHANG, Zhuming QIN, Jing WONG, Tien-Tsin HAN, Guoqiang HE, Shengfeng |
author_sort |
XIAO, Chufeng |
title |
Example-based colourization via dense encoding pyramids |
title_short |
Example-based colourization via dense encoding pyramids |
title_full |
Example-based colourization via dense encoding pyramids |
title_fullStr |
Example-based colourization via dense encoding pyramids |
title_full_unstemmed |
Example-based colourization via dense encoding pyramids |
title_sort |
example-based colourization via dense encoding pyramids |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/7837 https://ink.library.smu.edu.sg/context/sis_research/article/8840/viewcontent/example_based.pdf |
_version_ |
1770576553476882432 |