Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing

Published 16 Sept 2026arXiv:2609.14657

data quality89

Updated 7 h ago · first seen 15 Sept 2026

paper_01M2JK19B69AT3C7T4XAXA6NJR

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.

Authors

Authors 6

Dohyun KimGeonhee HanPaul Hongsuck SeoSehwan ParkSeung Wook KimTaehoon Kim

Linked names open researcher pages (created from the paper's author list; name-only, no affiliation unless a source states it). Unlinked names have no researcher record yet.

Organizations

Organizations 0

No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.

Models

Models introduced or described 0

Inbound described_by relations from model cards and documentation.

No model links this paper yet

Model pages link papers through their model cards and documentation; the relation is written only when a source states it.

Datasets

Datasets used 0

No dataset relation recorded.

Benchmarks

Benchmarks used 0

No benchmark relation recorded.

Code

Repositories & frameworks 0

No repository linked.

Timeline

Timeline 4

16 Sept 2026
Property changedPaperCompositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv
rss.arxiv.org
16 Sept 2026
Property changedPaperCompositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing: published at changed from 2026-09-15T04:00:00+00:00 to 2026-09-16T04:00:00+00:00
Published15 Sept 2026→16 Sept 2026arxiv
rss.arxiv.org
15 Sept 2026
Property changedPaperCompositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv
rss.arxiv.org
15 Sept 2026
New paperPaperCompositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
New paper: Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
arxiv
rss.arxiv.org

Full timeline →

Sources

Sources 2

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CV	feed	T1· Official	7 h ago	4
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	7 h ago	5

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.