Text-Guided Vector Graphics Customization

1City University of Hong Kong, 2Adobe Research
Teaser image.

Our results on text-guided vector graphics customization. Given an exemplar vector graphic in the SVG format (a), our model can generate customized vector graphics (b) based on the diverse text inputs while keep the visual identity V* of the exemplar SVG.

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.

Methods

Text-Guided vector graphics customization pipeline. Given an exemplar SVG and a text prompt as input (a), the method consists of three stages. (b) Concept Fine-tuning: By fine-tuning a pre-trained T2I model, a customized raster image is generated based on the text prompt. (c) Path Alignment: Important paths from the exemplar SVG are adapted based on semantic correspondences with the customized raster image, providing an initial customized SVG. (d) Path Optimization: The path parameters are optimized using both image-level and vector-level losses to produce the final customized SVG (e).

Results

Results of text-guided vector graphics customizations

BibTeX


      @inproceedings{zhang2023text,
        title     = {Text-guided vector graphics customization},
        author    = {Zhang, Peiying and Zhao, Nanxuan and Liao, Jing},
        booktitle = {SIGGRAPH Asia 2023 Conference Papers},
        pages     = {1--11},
        year      = {2023}
      }