AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

Yiren Song, Danze Chen, Mike Zheng Shou

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 51 citations (OpenAlex)

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 changedWhereMeasuredEffect
add serpentine layout to the training grid (ablation)LayerTracer Image2Layers · Serpentine ablation (train)MSE: 2.03 x 10^-4 -> 1.65 x 10^-4Improved
add serpentine layout to the training grid (ablation)LayerTracer Image2Layers · Serpentine ablation (test)MSE: 2.41 x 10^-4 -> 1.96 x 10^-4Improved
add serpentine layout to the training grid (ablation)LayerTracer Image2Layers · Serpentine ablation (train)SSIM: 0.964 -> 0.971Improved
add serpentine layout to the training grid (ablation)LayerTracer Image2Layers · Serpentine ablation (test)SSIM: 0.959 -> 0.963Improved
LayerTracer vs optimization-based text-to-SVG baselines (SVGDreamer)text-to-SVG · Text-to-SVG (50 prompts)time cost (s): 5715 -> 27Improved
LayerTracer vs best CLIP baseline SVGDreamertext-to-SVG · Text-to-SVG (50 prompts)CLIP Score: 32.68 -> 33.76Improved
LayerTracer vs Diffvg for vectorization path countlayer-wise vectorization · Layer-wise vectorization (50 images)number of paths: 256.00 -> 29.98Improved
LayerTracer vs O&R for vectorization MSElayer-wise vectorization · Layer-wise vectorization (50 images)MSE: 2.01 x 10^-4 -> 1.96 x 10^-4Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy