VectorWeaver: Transformers-Based Diffusion Model for Vector Graphics Generation

Ivan Jarsky, Maxim Kuzin, Valeria Efimova, Viacheslav Shalamov, Andrey Filchenkov

2025

Abstract

Diffusion models generate realistic results for raster images. However, vector image generation is not so successful because of significant differences in image structure. Unlike raster images, vector ones consist of paths that are described by their coordinates, colors, and stroke widths. The number of paths needed to be generated is unknown in advance. We tackle the vector image synthesis problem by developing a new diffusion-based model architecture, that we call VectorWeaver, including two transformer-based stacked encoders and two transformer-based stacked decoders. For training the model, we collected a vector images dataset from public resources, however, its size was not enough. To enrich and enlarge it we proposed new augmentation operations specific for vector images. To train the model, we designed a specific loss function, which allowed the generation of objects with smooth contours without artifacts. Qualitative experiments demonstrate the superiority and computational efficiency of the proposed model compared to the existing vector image generation methods. The vector image generation code is available at https://github.com/CTLab-ITMO/VGLib/tree/main/VectorWeaver.

Paper Citation

in Harvard Style

Jarsky I., Kuzin M., Efimova V., Shalamov V. and Filchenkov A. (2025). VectorWeaver: Transformers-Based Diffusion Model for Vector Graphics Generation. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 184-195. DOI: 10.5220/0013185100003912

in Bibtex Style

@conference{visapp25,
author={Ivan Jarsky and Maxim Kuzin and Valeria Efimova and Viacheslav Shalamov and Andrey Filchenkov},
title={VectorWeaver: Transformers-Based Diffusion Model for Vector Graphics Generation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={184-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013185100003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - VectorWeaver: Transformers-Based Diffusion Model for Vector Graphics Generation
SN - 978-989-758-728-3
AU - Jarsky I.
AU - Kuzin M.
AU - Efimova V.
AU - Shalamov V.
AU - Filchenkov A.
PY - 2025
SP - 184
EP - 195
DO - 10.5220/0013185100003912
PB - SciTePress