Depth-aware image colorization network

Wei Ta Chu, Yu Ting Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The color bleeding problem remains a challenging issue in image colorization. That is, different objects share the same color when they are nearby, leading to the boundary between objects looks unnatural. In this paper, we study how to combine depth information into a neural network and achieve better image colorization. The reasons to integrate depth information are twofold: (1) Depth information clearly provides boundary information between objects, and (2) depth information is commonly available as the development of RGB-D cameras. To the best of our knowledge, depth information was not considered in image colorization before. We evaluate the proposed method from both objective and subjective perspectives, and demonstrate that better colorization results can be obtained when depth information is further considered.

Original languageEnglish
Title of host publicationEE-USAD 2018 - Proceedings of the 2018 Workshop on Understanding Subjective Attributes of Data, with the Focus on Evoked Emotions, co-located with MM 2018
PublisherAssociation for Computing Machinery, Inc
Pages17-23
Number of pages7
ISBN (Electronic)9781450359788
DOIs
Publication statusPublished - 2018 Oct 15
Event2018 Workshop on Understanding Subjective Attributes of Data, with the Focus on Evoked Emotions, EE-USAD 2018, in conjunction with ACM Multimedia, MM 2018 - Seoul, Korea, Republic of
Duration: 2018 Oct 22 → …

Publication series

NameEE-USAD 2018 - Proceedings of the 2018 Workshop on Understanding Subjective Attributes of Data, with the Focus on Evoked Emotions, co-located with MM 2018

Conference

Conference2018 Workshop on Understanding Subjective Attributes of Data, with the Focus on Evoked Emotions, EE-USAD 2018, in conjunction with ACM Multimedia, MM 2018
CountryKorea, Republic of
CitySeoul
Period18-10-22 → …

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Depth-aware image colorization network'. Together they form a unique fingerprint.

  • Cite this

    Chu, W. T., & Hsu, Y. T. (2018). Depth-aware image colorization network. In EE-USAD 2018 - Proceedings of the 2018 Workshop on Understanding Subjective Attributes of Data, with the Focus on Evoked Emotions, co-located with MM 2018 (pp. 17-23). (EE-USAD 2018 - Proceedings of the 2018 Workshop on Understanding Subjective Attributes of Data, with the Focus on Evoked Emotions, co-located with MM 2018). Association for Computing Machinery, Inc. https://doi.org/10.1145/3267799.3267800