Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Pixelated semantic colorization

Tools
- Tools
+ Tools

Zhao, Jiaojiao, Han, Jungong, Shao, Ling and Snoek, Cees G. M. (2020) Pixelated semantic colorization. International Journal of Computer Vision, 128 . 818-834 . doi:10.1007/s11263-019-01271-4

[img]
Preview
PDF
WRAP-pixelated-semantic-colorization-Han-2019.pdf - Published Version - Requires a PDF viewer.
Available under License Creative Commons Attribution 4.0.

Download (4Mb) | Preview
Official URL: http://doi.org/10.1007/s11263-019-01271-4

Request Changes to record.

Abstract

While many image colorization algorithms have recently shown the capability of producing plausible color versions from grayscale photographs, they still suffer from limited semantic understanding. To address this shortcoming, we propose to exploit
pixelated object semantics to guide image colorization. The rationale is that human beings perceive and distinguish colors
based on the semantic categories of objects. Starting from an autoregressive model, we generate image color distributions, from
which diverse colored results are sampled. We propose two ways to incorporate object semantics into the colorization model:
through a pixelated semantic embedding and a pixelated semantic generator. Specifically, the proposed network includes two
branches. One branch learns what the object is, while the other branch learns the object colors. The network jointly optimizes
a color embedding loss, a semantic segmentation loss and a color generation loss, in an end-to-end fashion. Experiments on
Pascal VOC2012 and COCO-stuff reveal that our network, when trained with semantic segmentation labels, produces more
realistic and finer results compared to the colorization state-of-the-art.

Item Type: Journal Article
Subjects: Q Science > QA Mathematics
T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TR Photography
Divisions: Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group)
Library of Congress Subject Headings (LCSH): Computer vision -- Research, Photographs -- Coloring, Image processing -- Digital techniques, Semantic computing
Journal or Publication Title: International Journal of Computer Vision
Publisher: Springer
ISSN: 0920-5691
Official Date: April 2020
Dates:
DateEvent
April 2020Published
7 December 2019Available
25 November 2019Accepted
Volume: 128
Page Range: 818-834
DOI: 10.1007/s11263-019-01271-4
Status: Peer Reviewed
Publication Status: Published
Reuse Statement (publisher, data, author rights): This is a post-peer-review, pre-copyedit version of an article published in International Journal of Computer Vision. The final authenticated version is available online at: http://dx.doi.org/10.1007/s11263-019-01271-4
Access rights to Published version: Open Access

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us