VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors

2024-05-05

AI Summary

To address the challenge of reproducing specific artistic styles in text-to-vector generation—a limitation of existing methods—this paper introduces the first reference-image-guided, text-driven vector graphic synthesis framework. Methodologically, we propose a novel imitation learning–based stroke vectorization strategy that decomposes a reference image into differentiable, optimizable vector strokes; we further design a style-preserving loss to explicitly model artist-specific stylistic priors as transferable and differentiable components within the vector generation process. By jointly optimizing stroke geometry, color, and topology under textual constraints, our approach synthesizes high-fidelity vector graphics. Extensive evaluations across multiple benchmarks demonstrate substantial improvements over state-of-the-art methods, achieving superior style consistency and semantic alignment. Moreover, the fully differentiable pipeline enables end-to-end vector editing.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We introduce VectorPainter, a novel framework designed for reference-guided text-to-vector-graphics synthesis. Based on our observation that the style of strokes can be an important aspect to distinguish different artists, our method reforms the task into synthesize a desired vector graphics by rearranging stylized strokes, which are vectorized from the reference images. Specifically, our method first converts the pixels of the reference image into a series of vector strokes, and then generates a vector graphic based on the input text description by optimizing the positions and colors of these vector strokes. To precisely capture the style of the reference image in the vectorized strokes, we propose an innovative vectorization method that employs an imitation learning strategy. To preserve the style of the strokes throughout the generation process, we introduce a style-preserving loss function. Extensive experiments have been conducted to demonstrate the superiority of our approach over existing works in stylized vector graphics synthesis, as well as the effectiveness of the various components of our method.

Problem

• Text-to-Image
• Artistic Style Transfer
• Vector Graphics

Innovation

• VectorPainter
• Style Transfer
• Vector Graphics