Depth-aware image colorization network

Wei Ta Chu, Yu Ting Hsu

研究成果: Conference contribution

摘要

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.

原文English
主出版物標題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
發行者Association for Computing Machinery, Inc
頁面17-23
頁數7
ISBN(電子)9781450359788
DOIs
出版狀態Published - 2018 十月 15
事件2018 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
持續時間: 2018 十月 22 → …

出版系列

名字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

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
國家Korea, Republic of
城市Seoul
期間18-10-22 → …

All Science Journal Classification (ASJC) codes

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

指紋 深入研究「Depth-aware image colorization network」主題。共同形成了獨特的指紋。

引用此