PaperScope
LIVE · 2026-09-15 05:40 UTC

Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing

Sehwan Park, Taehoon Kim, Geonhee Han, Dohyun Kim, Seung Wook Kim, Paul Hongsuck Seo

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.14657 v1
Category
Submitted
2026-09-13

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.

Comment: 26 pages, Accepted to EMNLP 2026 (Main)

arXiv abs page · PDF · same-day batch