SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Siqi, Dong, Xinyu, Xu, Haolei, Wu, Xingyu, Tang, Fei, Zhang, Hang, Yan, Yuchen, Wu, Linjuan, Zhang, Wenqi, Hou, Guiyang, Shen, Yongliang, Lu, Weiming, Zhuang, Yueting
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916776232615936
author Chen, Siqi
Dong, Xinyu
Xu, Haolei
Wu, Xingyu
Tang, Fei
Zhang, Hang
Yan, Yuchen
Wu, Linjuan
Zhang, Wenqi
Hou, Guiyang
Shen, Yongliang
Lu, Weiming
Zhuang, Yueting
author_facet Chen, Siqi
Dong, Xinyu
Xu, Haolei
Wu, Xingyu
Tang, Fei
Zhang, Hang
Yan, Yuchen
Wu, Linjuan
Zhang, Wenqi
Hou, Guiyang
Shen, Yongliang
Lu, Weiming
Zhuang, Yueting
contents Large Language Models (LLMs) and Multimodal LLMs have shown promising capabilities for SVG processing, yet existing benchmarks suffer from limited real-world coverage, lack of complexity stratification, and fragmented evaluation paradigms. We introduce SVGenius, a comprehensive benchmark comprising 2,377 queries across three progressive dimensions: understanding, editing, and generation. Built on real-world data from 24 application domains with systematic complexity stratification, SVGenius evaluates models through 8 task categories and 18 metrics. We assess 22 mainstream models spanning different scales, architectures, training paradigms, and accessibility levels. Our analysis reveals that while proprietary models significantly outperform open-source counterparts, all models exhibit systematic performance degradation with increasing complexity, indicating fundamental limitations in current approaches; however, reasoning-enhanced training proves more effective than pure scaling for overcoming these limitations, though style transfer remains the most challenging capability across all model types. SVGenius establishes the first systematic evaluation framework for SVG processing, providing crucial insights for developing more capable vector graphics models and advancing automated graphic design applications. Appendix and supplementary materials (including all data and code) are available at https://zju-real.github.io/SVGenius.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
Chen, Siqi
Dong, Xinyu
Xu, Haolei
Wu, Xingyu
Tang, Fei
Zhang, Hang
Yan, Yuchen
Wu, Linjuan
Zhang, Wenqi
Hou, Guiyang
Shen, Yongliang
Lu, Weiming
Zhuang, Yueting
Computer Vision and Pattern Recognition
Artificial Intelligence
Large Language Models (LLMs) and Multimodal LLMs have shown promising capabilities for SVG processing, yet existing benchmarks suffer from limited real-world coverage, lack of complexity stratification, and fragmented evaluation paradigms. We introduce SVGenius, a comprehensive benchmark comprising 2,377 queries across three progressive dimensions: understanding, editing, and generation. Built on real-world data from 24 application domains with systematic complexity stratification, SVGenius evaluates models through 8 task categories and 18 metrics. We assess 22 mainstream models spanning different scales, architectures, training paradigms, and accessibility levels. Our analysis reveals that while proprietary models significantly outperform open-source counterparts, all models exhibit systematic performance degradation with increasing complexity, indicating fundamental limitations in current approaches; however, reasoning-enhanced training proves more effective than pure scaling for overcoming these limitations, though style transfer remains the most challenging capability across all model types. SVGenius establishes the first systematic evaluation framework for SVG processing, providing crucial insights for developing more capable vector graphics models and advancing automated graphic design applications. Appendix and supplementary materials (including all data and code) are available at https://zju-real.github.io/SVGenius.
title SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.03139