SOURCE-LINKED INTELLIGENCE

Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global