VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911013468635136 |
|---|---|
| author | Kuchař, Josef Kadlčík, Marek Spiegel, Michal Štefánik, Michal |
| author_facet | Kuchař, Josef Kadlčík, Marek Spiegel, Michal Štefánik, Michal |
| contents | We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15903 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics Kuchař, Josef Kadlčík, Marek Spiegel, Michal Štefánik, Michal Machine Learning We introduce a large-scale dataset for instruction-guided vector image editing, consisting of over 270,000 pairs of SVG images paired with natural language edit instructions. Our dataset enables training and evaluation of models that modify vector graphics based on textual commands. We describe the data collection process, including image pairing via CLIP similarity and instruction generation with vision-language models. Initial experiments with state-of-the-art large language models reveal that current methods struggle to produce accurate and valid edits, underscoring the challenge of this task. To foster research in natural language-driven vector graphic generation and editing, we make our resources created within this work publicly available. |
| title | VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.15903 |