mlsanityData to 14 Oct 2026

VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation

arXiv 2605.24398 ↗First posted 23 May 2026cs.CV cs.AI cs.GRcited by 0

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 11 of its 24 references that are in the map. First posted on arXiv 23 May 2026.

Builds on

11 of 24 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models13 Oct

Other references · 10

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  5. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  7. 2022Towards Layer-wise Image Vectorizationcited by 79
  8. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Modelcited by 74
  9. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 66
  10. 2016Effective Clipart Image Vectorization Through Direct Optimization of Bezigonscited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models
  2. 2024VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation
  3. 2026VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
  4. 2025LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization
  5. 2024A Formalization of Image Vectorization by Region Merging
  6. 2025VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics
  7. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
  8. 2026Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs