Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs

2026-08-25

AI Summary

研究通过约束迭代优化方法，结合视觉反馈、结构化编辑和约束解码技术，探索现有视觉-语言模型生成可缩放矢量图形的能力与局限。

Abstract

Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized images. We explore whether inference-time methods can unlock SVG generation capabilities in off-the-shelf vision-language models (VLMs). We systematically evaluate a constrained iterative refinement harness that combines visual feedback, structured editing, and constrained decoding to characterize the capabilities and limitations of current VLMs for SVG generation. Across multiple VLMs and generation settings, we find that constrained decoding improves compilation success rates, while iterative refinement reveals a deficit in visual reasoning and self-correction. Our results highlight both the promise and current limitations of using inference-time methods to adapt general-purpose VLMs for SVG generation.

Problem

• Scalable Vector Graphics
• vision-language models
• inference-time methods
• iterative refinement

Innovation

• constrained decoding
• iterative refinement
• visual feedback
• structured editing