LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911103826526208 |
|---|---|
| author | Song, Yiren Chen, Danze Shou, Mike Zheng |
| author_facet | Song, Yiren Chen, Danze Shou, Mike Zheng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01105 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer Song, Yiren Chen, Danze Shou, Mike Zheng Computer Vision and Pattern Recognition 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. |
| title | LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.01105 |