中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Active Colorization for Cartoon Line Drawings

文献类型:期刊论文

作者Chen, Shu-Yu1,2; Zhang, Jia-Qi3; Gao, Lin1,2; He, Yue1,2; Xia, Shihong1,2; Shi, Min3; Zhang, Fang-Lue4
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2022-02-01
卷号28期号:2页码:1198-1208
关键词Image color analysis Image segmentation Semantics Feature extraction Shape Machine learning Animation Active learning line drawing colorization region matching
ISSN号1077-2626
DOI10.1109/TVCG.2020.3009949
英文摘要In the animation industry, the colorization of raw sketch images is a vitally important but very time-consuming task. This article focuses on providing a novel solution that semiautomatically colorizes a set of images using a single colorized reference image. Our method is able to provide coherent colors for regions that have similar semantics to those in the reference image. An active-learning-based framework is used to match local regions, followed by mixed-integer quadratic programming (MIQP) which considers the spatial contexts to further refine the matching results. We efficiently utilize user interactions to achieve high accuracy in the final colorized images. Experiments show that our method outperforms the current state-of-the-art deep learning based colorization method in terms of color coherency with the reference image. The region matching framework could potentially be applied to other applications, such as color transfer.
资助项目Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; National Natural Science Foundation of China[61872440] ; CCF-Tencent Open Fund ; Tencent AI Lab Rhino-Bird Focused Research Program[JR202024] ; Beijing Municipal Natural Science Foundation[L182016] ; Youth Innovation Promotion Association CAS ; Victoria Early-Career Research Excellence Award
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000736740300001
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/18326]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Gao, Lin
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.North China Elect Power Univ, Beijing 102206, Peoples R China
4.Victoria Univ Wellington, Sch Engn & Comp Sci, Wellington 6012, New Zealand
推荐引用方式
GB/T 7714
Chen, Shu-Yu,Zhang, Jia-Qi,Gao, Lin,et al. Active Colorization for Cartoon Line Drawings[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2022,28(2):1198-1208.
APA Chen, Shu-Yu.,Zhang, Jia-Qi.,Gao, Lin.,He, Yue.,Xia, Shihong.,...&Zhang, Fang-Lue.(2022).Active Colorization for Cartoon Line Drawings.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,28(2),1198-1208.
MLA Chen, Shu-Yu,et al."Active Colorization for Cartoon Line Drawings".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 28.2(2022):1198-1208.

入库方式: OAI收割

来源:计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。