Visual Computing

University of Konstanz
ACM Trans. Graph.

Neural Image abstraction using long smoothing B-splines

D. Berio, M. Stroh, S. Calinon, F. Fol Leymarie, O. Deussen, A. Shamir
Teaser of Neural Image abstraction using long smoothing B-splines

Our method allows to optimize long and smooth B-Spline curves using DiffVG rasterization pipelines. Applications range from text stylization to image abstraction and vectorization.

Material

Paper (.pdf, 25.0MB)

Abstract

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.

BibTeX

@article{Berio2025NeuralImageabstraction,
  abstract   = {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.},
  address    = {New York, NY, USA},
  articleno  = {225},
  author     = {D. Berio, M. Stroh, S. Calinon, F. Fol Leymarie, O. Deussen, A. Shamir},
  doi        = {10.1145/3763345},
  issn       = {0730-0301},
  issue_date = {December 2025},
  journal    = {ACM Trans. Graph.},
  keywords   = {differentiable vector graphics, B-splines, diffusion, CLIP, long strokes},
  month      = {December},
  number     = {6},
  numpages   = {11},
  publisher  = {Association for Computing Machinery},
  title      = {Neural Image abstraction using long smoothing B-splines},
  url        = {https://doi.org/10.1145/3763345},
  volume     = {44},
  year       = {2025}
}