mlsanityData to 7 Oct 2026

OmniSVG: A Unified Scalable Vector Graphics Generation Model

arXiv 2504.06263 ↗First posted 8 Apr 2025cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

Scalable Vector Graphics (SVG) is an important image format widely adopted in graphic design because of their resolution independence and editability. The study of generating high-quality SVG has continuously drawn attention from both designers and researchers in the AIGC community. However, existing methods either produces unstructured outputs with huge computational cost or is limited to generating monochrome icons of over-simplified structures. To produce high-quality and complex SVG, we propose OmniSVG, a unified framework that leverages pre-trained Vision-Language Models (VLMs) for end-to-end multimodal SVG generation. By parameterizing SVG commands and coordinates into discrete tokens, OmniSVG decouples structural logic from low-level geometry for efficient training while maintaining the expressiveness of complex SVG structure. To further advance the development of SVG synthesis, we introduce MMSVG-2M, a multimodal dataset with two million richly annotated SVG assets, along with a standardized evaluation protocol for conditional SVG generation tasks. Extensive experiments show that OmniSVG outperforms existing methods and demonstrates its potential for integration into professional SVG design workflows.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Builds on 53 of its 72 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

53 of 72 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  9. 2025Qwen2.5-VL Technical Reportcited by 5,418
  10. 2024Qwen2.5 Technical Reportcited by 4,713
  11. 2024GPT-4o System Cardcited by 4,467
  12. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
38 more
  1. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  3. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  4. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  5. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  6. 2024Yi: Open Foundation Models by 01.AIcited by 706
  7. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  8. 2024PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funnelingcited by 420
  9. 2022The Stack: 3 TB of permissively licensed source codecited by 354
  10. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 344
  11. 2017A Neural Representation of Sketch Drawingscited by 311
  12. 2015A note on the evaluation of generative modelscited by 291
  13. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 284
  14. 2023LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planningcited by 206
  15. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  16. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
  17. 2024Visual In-Context Learning for Large Vision-Language Modelscited by 124
  18. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  19. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
  20. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  21. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  22. 2019A Learned Representation for Scalable Vector Graphicscited by 91
  23. 2024MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMscited by 89
  24. 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
  25. 2022Towards Layer-wise Image Vectorizationcited by 77
  26. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Modelcited by 75
  27. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 73
  28. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 63
  29. 2019FIGR: Few-shot Image Generation with Reptilecited by 54
  30. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  31. 2024DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMscited by 42
  32. 2021Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Conceptscited by 40
  33. 2022Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesiscited by 40
  34. 2023ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Modelcited by 38
  35. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Modelscited by 36
  36. 2022CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphicscited by 34
  37. 2024StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesiscited by 26
  38. 2024DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generationcited by 26

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 54.

71 papers.

Sort:

By area:

  1. 2026Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoningcited by 40
  2. 2025VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learningcited by 18
  3. 2025SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generationcited by 16
  4. 2025VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representationcited by 15
  5. 2025UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Modelscited by 14
  6. 2025InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Modelscited by 12
  7. 2026AutoFigure-Edit: Generating Editable Scientific Illustrationcited by 12
  8. 2026Multimodal OCR: Parse Anything from Documentscited by 12
  9. 2026Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedbackcited by 12
  10. 2026OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Modelscited by 10
  11. 2026GenClaw: Code-Driven Agentic Image Generationcited by 10
  12. 2025JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligencecited by 7
38 more
  1. 2025Symbolic Graphics Programming with Large Language Modelscited by 6
  2. 2025DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidancecited by 6
  3. 2026VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animationcited by 6
  4. 2025From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualizationcited by 5
  5. 2025ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesiscited by 5
  6. 2026Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestrationcited by 5
  7. 2026VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editingcited by 5
  8. 2026LottieGPT: Tokenizing Vector Animation for Autoregressive Generationcited by 5
  9. 2025From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustrationcited by 4
  10. 2026VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstructioncited by 3
  11. 2026VecGlypher: Unified Vector Glyph Generation with Language Modelscited by 3
  12. 2026IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Frameworkcited by 3
  13. 2026CodePercept: Code-Grounded Visual STEM Perception for MLLMscited by 3
  14. 2026GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoningcited by 3
  15. 2026OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Rewardcited by 3
  16. 2026AmodalSVG: Amodal Image Vectorization via Semantic Layer Peelingcited by 3
  17. 2026Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generationcited by 3
  18. 2025Vector Prism: Animating Vector Graphics by Stratifying Semantic Structurecited by 2
  19. 2026SVRepair: Structured Visual Reasoning for Automated Program Repaircited by 2
  20. 2026OmniLottie: Generating Vector Animations via Parameterized Lottie Tokenscited by 2
  21. 2026Visual-ERM: Reward Modeling for Visual Equivalencecited by 2
  22. 2026Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMscited by 2
  23. 2026GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generationcited by 2
  24. 2025MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Modelscited by 1
  25. 2025RoboSVG: A Unified Framework for Interactive SVG Generation with Multi-modal Guidancecited by 1
  26. 2025Illustrator's Depth: Monocular Layer Index Prediction for Image Decompositioncited by 1
  27. 2026Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modelingcited by 1
  28. 2026Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysiscited by 1
  29. 2026mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrievalcited by 1
  30. 2026PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoningcited by 1
  31. 2026AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstructioncited by 1
  32. 2026LiveSVG: Zero-Shot SVG Animation via Video Generationcited by 1
  33. 2026ReDesign: Recovering Editable Design Structures from Images via Agentic Decompositioncited by 1
  34. 2026DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editablecited by 1
  35. 2026SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generationcited by 1
  36. 2026A Scalable Vector Graphics Latent Spacecited by 1
  37. 2026Figures as Programs: Recursive Generation of Editable Scientific Figurescited by 1
  38. 2025One-shot Embroidery Customization via Contrastive LoRA Modulationcited by 0

50 most cited of 71 All 71 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models
  2. 2025SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation
  3. 2026VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
  4. 2025SVGen: Interpretable Vector Graphics Generation with Large Language Models
  5. 2023StarVector: Generating Scalable Vector Graphics Code from Images and Text
  6. 2024SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation
  7. 2024SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
  8. 2025SVGauge: Towards Human-Aligned Evaluation for SVG Generation