Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing

2026-09-13

AI Summary

为解决生成可编辑SVG的难题，提出了一种基于VLM的框架，通过层次语义解析生成结构化的SVG，并引入新的评估基准。

Abstract

While Vision-Language Models (VLMs) excel at visual reasoning, generating structured, editable Scalable Vector Graphics (SVG) remains a fundamental challenge. Existing pipelines predominantly yield flat, semantically agnostic collections of paths, where editing a single object requires manually identifying its constituent paths. To address this, we propose a VLM-driven agentic framework for semantic compositional SVG generation. Our pipeline recursively parses visual scenes into semantic and geometric hierarchies via top-down decomposition, visual grounding, and prompt-driven amodal occlusion recovery, ensuring each component is geometrically complete. Furthermore, we introduce the Semantic SVG Benchmark with human-annotated semantic groups and novel sub-component metrics (Semantic Recall/Precision, PERE) to explicitly evaluate structural compositionality and functional editability. Experiments show that our natively predicted structures surpass the upper bounds of existing flat-generation methods in both grouping quality and editability, while maintaining state-of-the-art visual fidelity.

Problem

• Scalable Vector Graphics
• Semantic Compositional Generation
• Editable SVG

Innovation

• VLM-driven framework
• semantic compositional SVG generation
• hierarchical semantic parsing
• Semantic SVG Benchmark
• functional editability