mlsanityData to 14 Oct 2026

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

arXiv 2502.01105 ↗First posted 3 Feb 2025cs.CVcited by 43

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer based framework that bridges this gap by learning designers' layered SVG creation processes from a novel dataset of sequential design operations. Our approach operates in two phases: First, a text-conditioned DiT generates multi-phase rasterized construction blueprints that simulate human design workflows. Second, layer-wise vectorization with path deduplication produces clean, editable SVGs. For image vectorization, we introduce a conditional diffusion mechanism that encodes reference images into latent tokens, guiding hierarchical reconstruction while preserving structural integrity. Extensive experiments demonstrate LayerTracer's superior performance against optimization-based and neural baselines in both generation quality and editability, effectively aligning AI-generated vectors with professional design cognition.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 30 of its 63 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

30 of 63 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024DiffSim: Taming Diffusion Models for Evaluating Visual Similarity19 Dec
  2. 2024Fast Personalized Text-to-Image Syntheses With Attention Injection17 Mar
  3. 2024Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model12 Mar
  4. 2024InstantID: Zero-shot Identity-Preserving Generation in Seconds15 Jan

Other references · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  5. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  6. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 410
  7. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 187
  8. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 159
  9. 2023SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generationcited by 143
  10. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 116
  11. 2019A Learned Representation for Scalable Vector Graphicscited by 91
  12. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 66
14 more
  1. 2025Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Taskscited by 63
  2. 2021Paint Transformer: Feed Forward Neural Painting with Stroke Predictioncited by 62
  3. 2024FonTS: Text Rendering with Typography and Style Controlscited by 40
  4. 2024ProcessPainter: Learn Painting Process from Sequence Datacited by 38
  5. 2024Stable-Hair: Real-World Hair Transfer via Diffusion Modelcited by 35
  6. 2022CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphicscited by 34
  7. 2024Text-to-Vector Generation with Neural Path Representationcited by 33
  8. 2020Multi-modal Attention for Speech Emotion Recognitioncited by 29
  9. 2024StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesiscited by 26
  10. 2020Deep Vectorization of Technical Drawingscited by 23
  11. 2024IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generationcited by 22
  12. 2024Anti-Reference: Universal and Immediate Defense Against Reference-Based Generationcited by 18
  13. 2024NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generationcited by 17
  14. 2023Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Regioncited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 18.

43 papers.

Sort:

By area:

  1. 2025EasyControl: Adding Efficient and Flexible Control for Diffusion Transformercited by 119
  2. 2025EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingcited by 45
  3. 2025OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Datacited by 32
  4. 2025Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Controlcited by 28
  5. 2025EasyText: Controllable Diffusion Transformer for Multilingual Text Renderingcited by 26
  6. 2025RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformerscited by 26
  7. 2025PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Datacited by 24
  8. 2025All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learningcited by 24
  9. 2026FastVMT: Eliminating Redundancy in Video Motion Transfercited by 23
  10. 2025Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generationcited by 14
  11. 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chainscited by 14
  12. 2025Mitty: Diffusion-based Human-to-Robot Video Generationcited by 14
31 more
  1. 2025OmniPSD: Layered PSD Generation with Diffusion Transformercited by 13
  2. 2026Group Editing: Edit Multiple Images in One Gocited by 11
  3. 2025WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generationcited by 9
  4. 2025SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generationcited by 8
  5. 2026PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motioncited by 8
  6. 2025Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceiverscited by 5
  7. 2025OmniRefiner: Reinforcement-Guided Local Diffusion Refinementcited by 5
  8. 2025The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignmentcited by 5
  9. 2025NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-based Image Editingcited by 4
  10. 2025IC-Effect: Precise and Efficient Video Effects Editing via In-Context Learningcited by 4
  11. 2025Loom: Diffusion-Transformer for Interleaved Generationcited by 4
  12. 2026OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptationcited by 4
  13. 2025MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformercited by 3
  14. 2026ReMoT: Reinforcement Learning with Motion Contrast Tripletscited by 3
  15. 2026AmodalSVG: Amodal Image Vectorization via Semantic Layer Peelingcited by 3
  16. 2026Deltaynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videoscited by 3
  17. 2026SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokenscited by 2
  18. 2026Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMscited by 2
  19. 2026EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generationcited by 2
  20. 2025Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoisingcited by 1
  21. 2025Illustrator's Depth: Monocular Layer Index Prediction for Image Decompositioncited by 1
  22. 2025Image Generation as a Visual Planner for Robotic Manipulationcited by 1
  23. 2025TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidancecited by 1
  24. 2026mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrievalcited by 1
  25. 2026ReDesign: Recovering Editable Design Structures from Images via Agentic Decompositioncited by 1
  26. 2026GenPuzzle: Benchmarking Visual Reasoning in Image Generation Modelscited by 1
  27. 2026Uni-Animator: Towards Unified Visual Colorizationcited by 0
  28. 2026SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Iconscited by 0
  29. 2026LimeCross: Context-Conditioned Layered Image Editing with Structural Consistencycited by 0
  30. 2026SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generationcited by 0
  31. 2026VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphicscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LayerCanvas: Infographic Generation in AI Learning Assistants via Hybrid Layer-Set Diffusion
  2. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
  3. 2024SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation
  4. 2024CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion
  5. 2026VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
  6. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
  7. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Model
  8. 2025Style Customization of Text-to-Vector Generation with Image Diffusion Priors