Neural Image Abstraction Using Long Smoothing B-Splines

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Berio, Daniel, Stroh, Michael, Calinon, Sylvain, Leymarie, Frederic Fol, Deussen, Oliver, Shamir, Ariel
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909892900552704
author Berio, Daniel
Stroh, Michael
Calinon, Sylvain
Leymarie, Frederic Fol
Deussen, Oliver
Shamir, Ariel
author_facet Berio, Daniel
Stroh, Michael
Calinon, Sylvain
Leymarie, Frederic Fol
Deussen, Oliver
Shamir, Ariel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05360
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Image Abstraction Using Long Smoothing B-Splines
Berio, Daniel
Stroh, Michael
Calinon, Sylvain
Leymarie, Frederic Fol
Deussen, Oliver
Shamir, Ariel
Graphics
Computer Vision and Pattern Recognition
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.
title Neural Image Abstraction Using Long Smoothing B-Splines
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.05360