Text-Guided Vector Graphics Customization

TL;DR

This paper presents a new method for customizing vector graphics using text prompts, combining fine-tuning of pre-trained models with semantic path alignment to produce high-quality, personalized SVGs while preserving original properties.

Contribution

It introduces a novel pipeline that leverages large pre-trained text-to-image models and semantic path alignment for effective vector graphic customization from textual descriptions.

Findings

Generated vector graphics show high diversity and quality.

The method preserves exemplar SVG properties during customization.

Evaluation confirms the approach's effectiveness across multiple metrics.

Abstract

Vector graphics are widely used in digital art and valued by designers for their scalability and layer-wise topological properties. However, the creation and editing of vector graphics necessitate creativity and design expertise, leading to a time-consuming process. In this paper, we propose a novel pipeline that generates high-quality customized vector graphics based on textual prompts while preserving the properties and layer-wise information of a given exemplar SVG. Our method harnesses the capabilities of large pre-trained text-to-image models. By fine-tuning the cross-attention layers of the model, we generate customized raster images guided by textual prompts. To initialize the SVG, we introduce a semantic-based path alignment method that preserves and transforms crucial paths from the exemplar SVG. Additionally, we optimize path parameters using both image-level and vector-level losses, ensuring smooth shape deformation while aligning with the customized raster image. We extensively evaluate our method using multiple metrics from vector-level, image-level, and text-level perspectives. The evaluation results demonstrate the effectiveness of our pipeline in generating diverse customizations of vector graphics with exceptional quality. The project page is https://intchous.github.io/SVGCustomization.