InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer
IEEE Transactions on Circuits and Systems for Video Technology · 2024-04 · 34 (4) · 2070-2082
DOI: 10.1109/tcsvt.2023.3300906 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-04. Verfasst von Yueming Lyu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content image. Although effective, ignoring the clear disentanglement of the content features and the style features from the first beginning, they have difficulty in balancing between content preservation and style transferring. To tackle this problem, we propose a novel information disentanglement method, named InfoStyler, to capture the minimal sufficient information for both content and style representations from the pre-trained encoding network. InfoStyler formulates the disentanglement representation learning as an information compression problem by eliminating style statistics from the content image and removing the content structure from the style image. Besides, to further facilitate disentanglement learning, a cross-domain Information Bottleneck (IB) learning strategy is proposed by reconstructing the content and style domains. Extensive experiments demonstrate that our InfoStyler can synthesize high-quality stylized images while balancing content structure preservation and style pattern richness.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
- Young Elite Scientists Sponsorship Program (YESS) by China Association for Science and Technology
Zitieren
APA
Lyu, Y., Jiang, Y., Peng, B., & Dong, J. (2024). InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer. IEEE Transactions on Circuits and Systems for Video Technology, 34(4), 2070-2082. https://doi.org/10.1109/tcsvt.2023.3300906
Vancouver
Lyu Y, Jiang Y, Peng B, Dong J. InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(4):2070-2082. doi:10.1109/tcsvt.2023.3300906
BibTeX
@article{Lyu2024,
author = {Lyu, Yueming and Jiang, Yue and Peng, Bo and Dong, Jing},
title = {InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {34},
number = {4},
pages = {2070--2082},
doi = {10.1109/tcsvt.2023.3300906}
}
EUVIMED