Neural Image abstraction using long smoothing B-splines
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-11
DOI: 10.1145/3763345 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Daniel Berio und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: UKRI/AHRC, Deutsche Forschungsgemeinschaft/DFG.
Abstract (Originalsprache)
We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems. We take advantage of derivative-based smoothing costs for parametric control of fidelity vs. simplicity tradeoffs, while also enabling stylization control in geometric and image spaces. The proposed pipeline is compatible with recent vector graphics generation and vectorization methods. We demonstrate the versatility of our approach with four applications aimed at the generation of stylized vector graphics: stylized space-filling path generation, stroke-based image abstraction, closed-area image abstraction, and stylized text generation.
Förderung
- UKRI/AHRC
- Deutsche Forschungsgemeinschaft/DFG
Zitieren
APA
Berio, D., Stroh, M., Calinon, S., Leymarie, F. F., Deussen, O., & Shamir, A. (2025). Neural Image abstraction using long smoothing B-splines. ACM Transactions on Graphics, 44(6), 1-11. https://doi.org/10.1145/3763345
Vancouver
Berio D, Stroh M, Calinon S, Leymarie FF, Deussen O, Shamir A. Neural Image abstraction using long smoothing B-splines. ACM Transactions on Graphics. 2025;44(6):1-11. doi:10.1145/3763345
BibTeX
@article{Berio2025,
author = {Berio, Daniel and Stroh, Michael and Calinon, Sylvain and Leymarie, Frederic Fol and Deussen, Oliver and Shamir, Ariel},
title = {Neural Image abstraction using long smoothing B-splines},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--11},
doi = {10.1145/3763345}
}
EUVIMED