Research map / Image generation / Text-to-image diffusion
LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
Yiren Song, Danze Chen, Mike Zheng Shou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add serpentine layout to the training grid (ablation) | LayerTracer Image2Layers · Serpentine ablation (train) | MSE: 2.03 x 10^-4 -> 1.65 x 10^-4 | Improved |
| add serpentine layout to the training grid (ablation) | LayerTracer Image2Layers · Serpentine ablation (test) | MSE: 2.41 x 10^-4 -> 1.96 x 10^-4 | Improved |
| add serpentine layout to the training grid (ablation) | LayerTracer Image2Layers · Serpentine ablation (train) | SSIM: 0.964 -> 0.971 | Improved |
| add serpentine layout to the training grid (ablation) | LayerTracer Image2Layers · Serpentine ablation (test) | SSIM: 0.959 -> 0.963 | Improved |
| LayerTracer vs optimization-based text-to-SVG baselines (SVGDreamer) | text-to-SVG · Text-to-SVG (50 prompts) | time cost (s): 5715 -> 27 | Improved |
| LayerTracer vs best CLIP baseline SVGDreamer | text-to-SVG · Text-to-SVG (50 prompts) | CLIP Score: 32.68 -> 33.76 | Improved |
| LayerTracer vs Diffvg for vectorization path count | layer-wise vectorization · Layer-wise vectorization (50 images) | number of paths: 256.00 -> 29.98 | Improved |
| LayerTracer vs O&R for vectorization MSE | layer-wise vectorization · Layer-wise vectorization (50 images) | MSE: 2.01 x 10^-4 -> 1.96 x 10^-4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- SVGDreamer — SVGDreamer: Text Guided SVG Generation with Diffusion Model (CVPR 2024) · better on 3 of 3 shared results
- Vecfusion — VecFusion: Vector Font Generation with Diffusion (CVPR 2024) · better on 3 of 3 shared results
- DiffSketcher — DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models (NeurIPS 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models (CVPR 2025 · similarity 0.86)
- OmniSVG: A Unified Scalable Vector Graphics Generation Model (NeurIPS 2025 · similarity 0.85)
- SVGDreamer: Text Guided SVG Generation with Diffusion Model (CVPR 2024 · similarity 0.85)
- SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformers (AAAI 2025 · similarity 0.83)
- Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation (CVPR 2024 · similarity 0.83)
- DrawingsDreamer: A Unified Multi-View Engineering Drawings Generation Model (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
