Preprint
Aug 2026
SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation
SVGEval is introduced, a vision-grounded multimodal benchmark for human-aligned SVG quality assessment that incorporates visual renderings to evaluate whether models can judge the rendered outcome rather than only inspect SVG code, and provides high-quality annotations obtained via multi-round human labeling with exper...
Yimin Wang, Ye Chen, Hanqi Chen et al.
· 1 citation