VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
This work addresses the practical challenge of vectorizing real-world images (e.g., from text-to-image models) for graphics applications, where previous methods fail due to synthetic benchmark overfitting.
VectorArk introduces a VLM-based model for robust image vectorization using a novel rounded polygon representation and a degradation model, achieving superior geometric completeness and artifact suppression across multiple datasets compared to prior methods.
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.