Painterly Image Harmonization by Learning from Painterly Objects
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4343-4351
DOI: 10.1609/aaai.v38i5.28231 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Li Niu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
Given a composite image with photographic object and painterly background, painterly image harmonization targets at stylizing the composite object to be compatible with the background. Despite the competitive performance of existing painterly harmonization works, they did not fully leverage the painterly objects in artistic paintings. In this work, we explore learning from painterly objects for painterly image harmonization. In particular, we learn a mapping from background style and object information to object style based on painterly objects in artistic paintings. With the learnt mapping, we can hallucinate the target style of composite object, which is used to harmonize encoder feature maps to produce the harmonized image. Extensive experiments on the benchmark dataset demonstrate the effectiveness of our proposed method.
Zitieren
APA
Niu, L., Cao, J., Hong, Y., & Zhang, L. (2024). Painterly Image Harmonization by Learning from Painterly Objects. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4343-4351. https://doi.org/10.1609/aaai.v38i5.28231
Vancouver
Niu L, Cao J, Hong Y, Zhang L. Painterly Image Harmonization by Learning from Painterly Objects. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4343-4351. doi:10.1609/aaai.v38i5.28231
BibTeX
@article{Niu2024,
author = {Niu, Li and Cao, Junyan and Hong, Yan and Zhang, Liqing},
title = {Painterly Image Harmonization by Learning from Painterly Objects},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {5},
pages = {4343--4351},
doi = {10.1609/aaai.v38i5.28231}
}
EUVIMED