VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gehlaut, Tarun, Liu, Difan, Bansal, Charu, Malani, Krutik, Chakraborty, Souymodip, Phogat, Ankit, Fisher, Matthew, Batra, Vineet
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918519504896000
author Gehlaut, Tarun
Liu, Difan
Bansal, Charu
Malani, Krutik
Chakraborty, Souymodip
Phogat, Ankit
Fisher, Matthew
Batra, Vineet
author_facet Gehlaut, Tarun
Liu, Difan
Bansal, Charu
Malani, Krutik
Chakraborty, Souymodip
Phogat, Ankit
Fisher, Matthew
Batra, Vineet
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24398
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
Gehlaut, Tarun
Liu, Difan
Bansal, Charu
Malani, Krutik
Chakraborty, Souymodip
Phogat, Ankit
Fisher, Matthew
Batra, Vineet
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
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.
title VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2605.24398