VecFusion: Vector Font Generation with Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thamizharasan, Vikas, Liu, Difan, Agarwal, Shantanu, Fisher, Matthew, Gharbi, Michael, Wang, Oliver, Jacobson, Alec, Kalogerakis, Evangelos
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916254976049152
author Thamizharasan, Vikas
Liu, Difan
Agarwal, Shantanu
Fisher, Matthew
Gharbi, Michael
Wang, Oliver
Jacobson, Alec
Kalogerakis, Evangelos
author_facet Thamizharasan, Vikas
Liu, Difan
Agarwal, Shantanu
Fisher, Matthew
Gharbi, Michael
Wang, Oliver
Jacobson, Alec
Kalogerakis, Evangelos
contents We present VecFusion, a new neural architecture that can generate vector fonts with varying topological structures and precise control point positions. Our approach is a cascaded diffusion model which consists of a raster diffusion model followed by a vector diffusion model. The raster model generates low-resolution, rasterized fonts with auxiliary control point information, capturing the global style and shape of the font, while the vector model synthesizes vector fonts conditioned on the low-resolution raster fonts from the first stage. To synthesize long and complex curves, our vector diffusion model uses a transformer architecture and a novel vector representation that enables the modeling of diverse vector geometry and the precise prediction of control points. Our experiments show that, in contrast to previous generative models for vector graphics, our new cascaded vector diffusion model generates higher quality vector fonts, with complex structures and diverse styles.
format Preprint
id arxiv_https___arxiv_org_abs_2312_10540
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle VecFusion: Vector Font Generation with Diffusion
Thamizharasan, Vikas
Liu, Difan
Agarwal, Shantanu
Fisher, Matthew
Gharbi, Michael
Wang, Oliver
Jacobson, Alec
Kalogerakis, Evangelos
Computer Vision and Pattern Recognition
Graphics
We present VecFusion, a new neural architecture that can generate vector fonts with varying topological structures and precise control point positions. Our approach is a cascaded diffusion model which consists of a raster diffusion model followed by a vector diffusion model. The raster model generates low-resolution, rasterized fonts with auxiliary control point information, capturing the global style and shape of the font, while the vector model synthesizes vector fonts conditioned on the low-resolution raster fonts from the first stage. To synthesize long and complex curves, our vector diffusion model uses a transformer architecture and a novel vector representation that enables the modeling of diverse vector geometry and the precise prediction of control points. Our experiments show that, in contrast to previous generative models for vector graphics, our new cascaded vector diffusion model generates higher quality vector fonts, with complex structures and diverse styles.
title VecFusion: Vector Font Generation with Diffusion
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2312.10540