SVGauge: Towards Human-Aligned Evaluation for SVG Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914027896045568 |
|---|---|
| author | Zini, Leonardo Frigieri, Elia Aloscari, Sebastiano Generali, Marcello Dodi, Lorenzo Dosen, Robert Baraldi, Lorenzo |
| author_facet | Zini, Leonardo Frigieri, Elia Aloscari, Sebastiano Generali, Marcello Dodi, Lorenzo Dosen, Robert Baraldi, Lorenzo |
| contents | Generated Scalable Vector Graphics (SVG) images demand evaluation criteria tuned to their symbolic and vectorial nature: criteria that existing metrics such as FID, LPIPS, or CLIPScore fail to satisfy. In this paper, we introduce SVGauge, the first human-aligned, reference based metric for text-to-SVG generation. SVGauge jointly measures (i) visual fidelity, obtained by extracting SigLIP image embeddings and refining them with PCA and whitening for domain alignment, and (ii) semantic consistency, captured by comparing BLIP-2-generated captions of the SVGs against the original prompts in the combined space of SBERT and TF-IDF. Evaluation on the proposed SHE benchmark shows that SVGauge attains the highest correlation with human judgments and reproduces system-level rankings of eight zero-shot LLM-based generators more faithfully than existing metrics. Our results highlight the necessity of vector-specific evaluation and provide a practical tool for benchmarking future text-to-SVG generation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07127 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SVGauge: Towards Human-Aligned Evaluation for SVG Generation Zini, Leonardo Frigieri, Elia Aloscari, Sebastiano Generali, Marcello Dodi, Lorenzo Dosen, Robert Baraldi, Lorenzo Graphics Artificial Intelligence Computer Vision and Pattern Recognition Generated Scalable Vector Graphics (SVG) images demand evaluation criteria tuned to their symbolic and vectorial nature: criteria that existing metrics such as FID, LPIPS, or CLIPScore fail to satisfy. In this paper, we introduce SVGauge, the first human-aligned, reference based metric for text-to-SVG generation. SVGauge jointly measures (i) visual fidelity, obtained by extracting SigLIP image embeddings and refining them with PCA and whitening for domain alignment, and (ii) semantic consistency, captured by comparing BLIP-2-generated captions of the SVGs against the original prompts in the combined space of SBERT and TF-IDF. Evaluation on the proposed SHE benchmark shows that SVGauge attains the highest correlation with human judgments and reproduces system-level rankings of eight zero-shot LLM-based generators more faithfully than existing metrics. Our results highlight the necessity of vector-specific evaluation and provide a practical tool for benchmarking future text-to-SVG generation models. |
| title | SVGauge: Towards Human-Aligned Evaluation for SVG Generation |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.07127 |