VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
About
Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then re-vectorized. As a result, these methods generalize poorly to real-world scenarios, such as images with unknown rasterization methods or those generated by text-to-image models. We introduce VectorArk, a new VLM-based model designed for robust and practical image vectorization. VectorArk employs a novel rounded polygon representation that simplifies the learning process while naturally producing smooth, visually appealing primitives. We also propose a degradation model that enhances robustness across diverse and imperfect inputs. Our experiments show that, in contrast to previous methods, VectorArk achieves superior geometric completeness and artifact suppression across multiple datasets, with comprehensive ablations validating the contribution of each component.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Vectorization | SVG-Stack-Simple (Easy) | LPIPS0.0274 | 10 | |
| Image Vectorization | SVG-Fonts Simple (Easy) | LPIPS0.0217 | 10 | |
| Image Vectorization | SVG-Icons-Simple (Easy) | LPIPS0.0565 | 10 | |
| Image Vectorization | SVG-Emoji-Simple (Easy) | LPIPS0.0282 | 10 | |
| Image Vectorization | MMSVG-Icon Easy (test) | LPIPS0.0122 | 5 | |
| Image Vectorization | MMSVG-Icon Med (test) | LPIPS0.0179 | 5 | |
| Image Vectorization | MMSVG-Icon Hard (test) | LPIPS0.0324 | 5 | |
| Image Vectorization | SVGX core 250k Easy (test) | LPIPS0.0168 | 5 | |
| Image Vectorization | SVGX core 250k Med (test) | LPIPS0.0332 | 5 | |
| Image Vectorization | SVGX_core_250k Hard (test) | LPIPS0.0677 | 5 |