Active Colorization for Cartoon Line Drawings

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 c...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 28(2022), 2 vom: 30. Feb., Seite 1198-1208
1. Verfasser: Chen, Shu-Yu (VerfasserIn)
Weitere Verfasser: Zhang, Jia-Qi, Gao, Lin, He, Yue, Xia, Shihong, Shi, Min, Zhang, Fang-Lue
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM313215987
003 DE-627
005 20231225150111.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2020.3009949  |2 doi 
028 5 2 |a pubmed24n1044.xml 
035 |a (DE-627)NLM313215987 
035 |a (NLM)32746275 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chen, Shu-Yu  |e verfasserin  |4 aut 
245 1 0 |a Active Colorization for Cartoon Line Drawings 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 31.12.2021 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a 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 
650 4 |a Journal Article 
700 1 |a Zhang, Jia-Qi  |e verfasserin  |4 aut 
700 1 |a Gao, Lin  |e verfasserin  |4 aut 
700 1 |a He, Yue  |e verfasserin  |4 aut 
700 1 |a Xia, Shihong  |e verfasserin  |4 aut 
700 1 |a Shi, Min  |e verfasserin  |4 aut 
700 1 |a Zhang, Fang-Lue  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 28(2022), 2 vom: 30. Feb., Seite 1198-1208  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnns 
773 1 8 |g volume:28  |g year:2022  |g number:2  |g day:30  |g month:02  |g pages:1198-1208 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2020.3009949  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 28  |j 2022  |e 2  |b 30  |c 02  |h 1198-1208