VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913871410757632 |
|---|---|
| author | Hu, Juncheng Xing, Ximing Zhang, Jing Yu, Qian |
| author_facet | Hu, Juncheng Xing, Ximing Zhang, Jing Yu, Qian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02962 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors Hu, Juncheng Xing, Ximing Zhang, Jing Yu, Qian Computer Vision and Pattern Recognition 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. |
| title | VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.02962 |